VisaTM étude Recensement d'outils de fouille de textes

Mise à jour du 25 mars 2019 Inist - F. Arnould | 1 Outil Description Licence Tâche(s) OMTD Source Pays

ABBYY ABBYY technologies and platforms for Commercial Classification de Non https://www.abbyy.com/en-eu/ Russie ; Solutions document recognition, data capture, and textes ; language processing. Reconnaissance d'entités nommées ; Découverte de connaissances ; Traduction automatique ; Recherche d'information ; ABNER ABNER is a software tool for molecular Libre Reconnaissance Oui http://pages.cs.wisc.edu/~bsettles/ États-Unis ; biology text analysis. d'entités nommées ; abner/ Abzooba Social media and text analytics software Commercial Analyse de Non http://www.abzooba.com/ États-Unis ; sentiments ; Classification ; Reconnaissance d'entités nommées ; ADAM Data Mining and Image Processing Libre Classification ; Nom http://projects.itsc.uah.edu/ États-Unis ; Toolkits Clustering ; datamining/adam/ Reconnaissance de forme ; Règles d'association ; Optimisation ; Traitement d'images ;

AdaMSoft ADaMSoft is a free and Open-Source Libre Classification ; Non http://adamsoft.sourceforge.net/ Italie ; System for Data Management, Data and Clustering ; Web Mining, statistical Analyis and more. Analyse de régression ; ai-one Transforms big data into opportunity Commercial Apprentissage Non http://www.ai-one.com/ États-Unis ; using machine learning that mimics the automatique ; Suisse ; biological brain’s ability to find patterns Allemagne ; and relationships.

Mise à jour du 25 mars 2019 Inist - F. Arnould | 2 Outil Description Licence Tâche(s) OMTD Source Pays

Aika Java library that automatically extracts Libre Annotation ; Non http://www.aika-software.org Allemagne ; and annotates semantic information into Désambiguïsation ; text Catégorisation de textes ; Reconnaissance d'entités nommées ; Extraction d'information ;

Alceste logiciel d'analyse de données textuelles, Commercial Classification ; Non http://www.image-zafar.com/ France ; ou statistique textuelle Logiciel.html AllenNLP An open-source NLP research library, built Libre Etiquetage Non http://allennlp.org/ États-Unis ; on PyTorch. sémantique ; Reconnaissance d'entités nommées ; Q&A ; Résolution de coréférence ; Textual entailment ; Constituency parsing ; Alteryx Project Predictive for Project Edition Commercial Prétraitement ; Non https://www.alteryx.com/fr/ États-Unis ; Edition Apprentissage predictive-project-edition automatique ; Alveo Alveo connects HCS (Human ? Recherche Non http://alveo.edu.au/ Australie ; Communication Science) researchers, d'informations ; their desks, computers, labs, and Reconnaissance de universities and accelerates HCS research la parole ; to produce emergent knowledge that Annotation ; comes from novel application of previously unshared tools to analyse previously difficult to access data sets.

Mise à jour du 25 mars 2019 Inist - F. Arnould | 3 Outil Description Licence Tâche(s) OMTD Source Pays

Alvis NLP A pipeline framework for Natural Libre Annotation ; Oui http://www.quaero.org/ France ; Language Processing Classification ; module_technologique/alvis-nlp- Allemagne ; Clustering ; alvis-natural-language-processing/ Q&A ; Traduction ; Recherche d'information ; Analyse de sentiments ; Analyse d'opinions ; Reconnaissance d'entités nommées ; Racinisation ; PoS tagging ; AMI Intégrateur de solutions logicielles de Commercial Traitement Non https://www.bertin-it.com/ France ; pointe automatique de la pour la Cybersécurité, la Cyber parole ; Recherche Intelligence, la Veille Stratégique d'informations ; et le Traitement Automatique de la Parole. Extraction de mots clés ; Annotation ;

Anaconda Python data science platform Libre/ Apprentissage Non https://www.anaconda.com/ États-Unis ; Commercial automatique ; Analec Annotation et analyse de corpus écrits Libre Annotation ; Non http://www.lattice.cnrs.fr/ France ; Telecharger-Analec Annomarket Cloud-based Text Annotation Commercial Annotation ; Non https://annomarket.eu/ ?

AntConc Freeware text analysis and concordance Libre Concordancier ; Non http://www.laurenceanthony.net/ Japon ; tool kit software/antconc/

Apache cTAKES Natural language processing system for Libre Extraction Non http://ctakes.apache.org/ États-Unis ; extraction of information from electronic d'information ; medical record clinical free-text. Annotation ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 4 Outil Description Licence Tâche(s) OMTD Source Pays

Apache Mahout Environment for quickly creating scalable Libre Architecture Non http://mahout.apache.org/ États-Unis ; performant machine learning applications. logicielle ; Analyse régression ; Clustering ; Apache The Apache OpenNLP library is a machine Libre Apprentissage Oui https://opennlp.apache.org/ États-Unis ; OpenNLP learning based toolkit for the processing automatique ; of natural language text. Lemmatisation ; Parsing ; Chunking ; Tokenisation ; PoS tagging ; Sentence splitting ; Reconnaissance d'entités nommées ; Résolution de coréférence ; Détection de la langue ; Classification ; Apache UIMA Component software architecture for the Libre Architecture Oui https://uima.apache.org/ États-Unis ; development, discovery, composition, and logicielle ; deployment of multi-modal analytics for the analysis of unstructured information and integration with search technologies. Argo Argo is a workbench for building and Libre Annotation ; Non http://argo.nactem.ac.uk/ Royaume- running text-analysis solutions. It Recherche Uni ; facilitates the development of custom d'informations ; workflows from a selection of elementary Reconnaissance analytics. d'entités nommées ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 5 Outil Description Licence Tâche(s) OMTD Source Pays

Ascribe Accelerate ROI via our surveys, vast Commercial Classification ; Non https://goascribe.com/ États-Unis ; sample and advanced text analytics Analyse d'opinions ; Analyse de sentiments ; Clustering ; Extraction d'informations ; ats Regression and clustering analysis Libre Clustering ; Non http://www.mepx.org/ ? Analyse de régression ; Averbis Averbis provides leading text mining and Commercial Découverte de Non https://averbis.com/en/ Allemagne ; machine learning solutions for your connaissances ; business. We convert text into Extraction information, automate cognitive terminologique ; processes, and make meaningful Reconnaissance predictions. d'entités nommées ; Classification de textes ; Analyse de sentiments ; Analyse d'opinions ; Recherche d'informations ; Aylien AI-driven content analysis solutions that Commercial Analyse de Non https://aylien.com/ Irlande ; bring the power of NLP to the masses. We sentiments ; help developers, data scientists, and Classifiation ; marketers understand human-generated Résumé textual content at scale. automatique ; Reconnaissance d'entités nommées ; Extraction d'informations ; Annotation ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 6 Outil Description Licence Tâche(s) OMTD Source Pays

Babel X Babel X® is a multi-lingual, geo-enabled, Commercial Analyse de Non https://www.babelstreet.com/ États-Unis ; text-analytics, social media and web- sentiments ; monitoring platform designed to meet the Clustering ; needs of our customers by fully leveraging Reconnaissance publicly available information in this era of d'entités nommées ; overwhelming quantities of geographically Extraction de diverse, multi-lingual data. relations ; Recherche d'informations ; BANNER Named entity recognition system Libre Reconnaissance Oui http://banner.sourceforge.net/ États-Unis ; d'entités nommées ; BioCreative BioCreative: Critical Assessment of Libre Reconnaissance Oui http://www.biocreative.org/events/ ? Information Extraction in Biology is a d'entités nommées ; biocreative-v/CFP/ community-wide effort for evaluating text Extraction de mining and information extraction relations ; systems applied to the biological domain Annotation ; BioLemmatizer The BioLemmatizer is a domain-specific Libre Lemmatisation ; Non http://biolemmatizer.sourceforge.net/ États-Unis ; lemmatization tool for the morphological analysis of biomedical literature. BioNLP BioNLP is an initiative by the Center for Libre Parsing ; Oui http://bionlp.sourceforge.net/ États-Unis ; Computational Pharmacology at the Lemmatisation ; University of Colorado Denver to create Annotation ; and distribute code, software, and data Classification de for applying natural language processing textes ; techniques to biomedical texts. Extraction d'informations ;

Biotex Biomedical term extraction Libre Extraction Non http://tubo.lirmm.fr/biotex/index.jsp France ; terminologique ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 7 Outil Description Licence Tâche(s) OMTD Source Pays

Bitext NLP Plateform Commercial Lemmatisation ; Non https://www.bitext.com/ Espagne ; PoS tagging ; Détection de la langue ; Extraction de phrases ; Reconnaissance d'entités nommées ; Analyse de sentiments ; Bluima Natural language processing toolkit for Libre Reconnaissance Non https://github.com/BlueBrain/bluima Suisse ; neuroscience d'entités nommées ; Brainspace Brainspace creates breakthrough machine Commercial Clustering ; Non https://www.brainspace.com/ États-Unis ; learning software that intelligently detects and relates unique phrases in massive unstructured datasets Brat Online environment for collaborative text Libre Extraction Oui http://brat.nlplab.org/ Japon ; annotation. d'information ; Royaume- Annotation ; Uni ; Reconnaissance d'entités nommées ; Bulstem Stemming for Bulgarian Libre Racinisation ; Oui https://github.com/peio/PyBulStem États-Unis ;

Caffe2 A new lightweight, modular, and scalable Libre Apprentissage Non https://caffe2.ai États-Unis ; deep learning framework profond ;

Calliope Logiciel d'analyse des tendances et de Libre/ Extraction Non https://www.calliope- France ; "fouille de textes" Support terminologique ; textmining.com/ technique et Analyse de formation tendances ; payants Analyse des co- occurrences ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 8 Outil Description Licence Tâche(s) OMTD Source Pays

Canopy Enthought Canopy provides a proven Commercial Appentissage Non https://store.enthought.com/basket/ États-Unis ; scientific and analytic Python package automatique ; distribution plus key integrated tools for iterative data analysis, data visualization, and application development. Users have the ability to extend and innovate with scripting and open platform APIs, driving the creation and sharing of innovative workflows, tools, and applications. Carrot2 Carrot2 organizes your search results into Libre Clustering ; Non http://search.carrot2.org/stable/ Pologne ; topics. With an instant overview of what's Recherche search Royaume- available, you will quickly find what you're d'informations ; Uni ; looking for. Chemicalize Chemicalize is a powerful online platform Libre Annotation ; Non https://chemicalize.com/welcome Hongrie ; for chemical calculations, search, and text Reconnaissance processing. d'entités nommées ; CiteSpace Visualizing Patterns and Trends in Libre Clustering ; Non http://cluster.cis.drexel.edu/~cchen/ États-Unis ; Scientific Literature citespace/

Clarabridge CX CX Analytics is the backbone of the Commercial Clustering ; Analyse Non https://www.clarabridge.com/ États-Unis ; Suite world’s most complex Customer de sentiments ; Experience Management Programs, Parsing ; Extraction providing the industry’s most accurate de relations ; Natural Language Processing (NLP), sentiment and data categorization, making issues transparent—and next steps clear. CX social : Social listening, rapid social media engagement, and social media analytics that empower teams of all sizes to wow customers and have a big impact.

Mise à jour du 25 mars 2019 Inist - F. Arnould | 9 Outil Description Licence Tâche(s) OMTD Source Pays

ClearNLP The ClearNLP project provides fast and Libre Tokenisation ; Oui http://clearnlp.wikispaces.com/ États-Unis ; robust NLP components implemented in Sentence splitting ; Java Parsing ; Etiquetage de rôles sémantiques ; PoS tagging ; ClearTK ClearTK is a framework for developing Libre Classification ; Non https://cleartk.github.io/cleartk/ États-Unis ; machine learning and natural language Clustering ; about.html processing components within the Parsing ; Apache Unstructured Information Racinisation ; Management Architecture. Tokenisation ; PoS tagging ; Feature extraction ; Clementine Clementine packages a number of tools Commercial Clustering ; Non http://datamining.togaware.com/ États-Unis ; with a GUI which simplifies the process of Classification ; survivor/Summary20.html performing a data mining project. In Analyse de particular the Clementine workbench régression ; supports a number of data mining algorithms through a simple linked node interface supporting the entire business process of data mining using the CRISP- DM model. CLUTO CLUTO is a software package for Libre Clustering ; Non http://glaros.dtc.umn.edu/gkhome/ États-Unis ; clustering low- and high-dimensional cluto/cluto/overview datasets and for analyzing the characteristics of the various clusters. CLUTO is well-suited for clustering data sets arising in many diverse application areas including information retrieval, customer purchasing transactions, web, GIS, science, and biology.

Mise à jour du 25 mars 2019 Inist - F. Arnould | 10 Outil Description Licence Tâche(s) OMTD Source Pays

CMSR Data Integrated environment for predictive Libre Classification ; Non http://www.roselladb.com/ Australie ; Miner modeling, segmentation, data Clustering ; starprobe.htm visualization, statistical data analysis, and rule-based model evaluation CogComp-NLP CogComp-NLP provides a suite of state- Libre Lemmatisation ; Non http://nlp.cogcomp.org/ États-Unis ; of-the-art Natural Language Processing PoS tagging ; (NLP) tools that allows you to annotate Parsing ; Extraction plain text inputs. de relations ; Reconnaissance d'entités nommées ; Etiquetage de rôles sémantiques ; Analyse de co- référence ; Cogito Multilingual text analytics, cognitive Commercial Reconnaissance Non http://www.expertsystem.com/fr/ Italie ; technology software that understands the d'entités nommées ; meaning of words in context. Classification ; Recherce d'informations ; Désambiguisation ; Extraction de mots clés ; Découverte de connaissances ; Cognitive Libre Reconnaissance Non http://cogcomp.org/page/software/ États-Unis ; Computation d'entités nommées ; Group NLP PoS tagging ; Tools Chunking ; Lemmatisation ; Etiquetage de rôles sémantiques ; Résolution de coréférence ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 11 Outil Description Licence Tâche(s) OMTD Source Pays

Coheris SPAD Pour l’analyse de données et le traitement Commercial Tokenisation ; Non https://www.coheris.com/produits/ France ; integral de toute l’information, notamment Lemmatisation ; analytics/logiciel-data-mining/ l’information textuelle. Classification ; analyse-de-donnees/ Clustering ; Arbre de décision ConcQuest Concordancier dédié à la recherche Libre Concordancier ; Non http://olivier.kraif.u-grenoble3.fr/ France ; d'expressions complexes à travers des Rercherche index.php? corpus monolingues et multilingues d'informations ; option=com_content&task=view&id= alignés. 36&Itemid=55 Content Create relevant metadata based on Commercial Annotation ; Non http://www.mondeca.com/content- France ; Annotation vocabularies and rules Reconnaissance annotation-manager/ Manager d'entités nommées ; ContentMine Text and data mining tools Libre Extraction de Non http://www.contentmine.org/text- Royaume- connaissances ; and-data-mining-tools/ Uni ; CORICO Outil de visualisation de données Commercial Découverte de Non http://www.coryent.com/corico.html France ; multifactorielles sans équivalent. A partir connaissances ; d'un tableau de données, "L'Iconographie des Corrélations" élimine les "fausses bonnes corrélations" (celles qui sont dues à une tierce variable), et révèle les corrélations "masquées" lorsqu'une variable dépend de plusieurs variables.

Cortex Manager CorText proposes a full ecosystem of Reconnaissance Non https://www.cortext.net/projects/ France ; modeling and exploratory tools for d'entités nommées ; cortext-manager/ analyzing text corpora. Topic modeling ; Extraction terminologique ; Apprentissage profond ; Clustering ; Analyse de sentiment ; Indexation ; Plongement de mots ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 12 Outil Description Licence Tâche(s) OMTD Source Pays

Databionic The Databionic ESOM Tools is a suite of Libre Classification ; Non http://databionic- Allemagne ; ESOM Tools programs to perform data mining tasks Clustering ; esom.sourceforge.net/ like clustering, visualization, and classification with Emergent Self- Organizing Maps Dataiku Dataiku DSS is the collaborative data Libre/ Clustering ; Non https://www.dataiku.com/ États-Unis ; science software platform for teams of Commercial data scientists, data analysts, and engineers to explore, prototype, build, and deliver their own data products more efficiently. DataMelt Free mathematics software for scientists, Libre/ Classification ; Non http://jwork.org/dmelt/ Allemagne ; engineers and students. It can be used for Commercial Clustering ; numeric computation, statistics, symbolic Analyse de calculations, data analysis and data régression ; visualization. DataPreparator DataPreparator is a free software tool Libre Prétraitement ; Non http://www.datapreparator.com/ Australie ; designed to assist with common tasks of data preparation (or data preprocessing) in data analysis and data mining. Datumbox The Datumbox Machine Learning Libre Classification ; Non http://www.datumbox.com/machine- Grèce Framework is an open-source framework Clustering ; learning-framework/ written in Java which allows the rapid Analyse de development of Machine Learning and régression ; Statistical applications. Analyse de sentiments ; Détection de la langue ; Extraction de mots clés ; Extraction de textes ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 13 Outil Description Licence Tâche(s) OMTD Source Pays

DBpedia It is a tool for automatically annotating Libre Annotation ; Non https://www.dbpedia-spotlight.org Allemagne ; Spotlight mentions of DBpedia resources in text, providing a solution for linking unstructured information sources to the Linked Open Data cloud through DBpedia. Deeplearning4j Eclipse Deeplearning4j is the first Libre Apprentissage Non https://deeplearning4j.org/ États-Unis ; commercial-grade, open-source, profond distributed deep-learning library written for Java and Scala. Integrated with Hadoop and Apache Spark, DL4J brings AI to business environments for use on distributed GPUs and CPUs.Deep learning Diction DICTION 7 is a computer-aided text Commercial Analyse de Non https://www.dictionsoftware.com/ États-Unis ; analysis program for determining the tone sentiments ; of a verbal message Digimind Social media analytics Commercial Clustering ; Non http://www.digimind.com/fr/ France ; Traduction automatique ; Annotation ; Analyse de sentiments ; Recherche d'informations ; Discovertext With dozens of powerful text analytics, Commercial Classification ; Non https://discovertext.com/ États-Unis ; data science, human coding, and machine-learning features, including instant access to the Gnip PowerTrack 2.0 for Twitter and the free Twitter Search API, DiscoverText provides cloud-based software tools to quickly evaluate large amounts of text, survey, and Twitter data.

Mise à jour du 25 mars 2019 Inist - F. Arnould | 14 Outil Description Licence Tâche(s) OMTD Source Pays

DKPro Core A collection of software components for Libre PoS tagging : Oui https://dkpro.github.io/dkpro-core/ Allemagne ; natural language processing (NLP) based Tokenisation ; on the Apache UIMA framework. Parsing ; Lemmatisation ; Etiquetage des rôles sémantiques ; Segmentation ; Reconnaissance d'entités nommées ; Chunking ; Racinisation ; Identification de langue ; Résolution de coréférence ; Apprentissage profond ; Analyse morphologique ; Clustering ; Annotation ; Dlib Dlib is a modern C++ toolkit containing Libre Apprentissage Non http://dlib.net/ États-Unis ; machine learning algorithms and tools for profond ; creating complex software in C++ to solve Classification ; real world problems. Clustering ; Dtm-Vic Statistique Exploratoire Libre Classification ; Non http://www.dtmvic.com/ France ; Multidimensionnelle pour données 05_SoftwareF.html complexes comprenant des données numériques et textuelles. Egas Collaborative biomedical text annotation. Libre Annotation ; Non https://demo.bmd-software.com/ Portugal ; Extraction de egas/ concepts ; Extraction de relations

Mise à jour du 25 mars 2019 Inist - F. Arnould | 15 Outil Description Licence Tâche(s) OMTD Source Pays

ELKI ELKI is an open source (AGPLv3) data Libre Clustering ; Non https://elki-project.github.io/ Allemagne ; mining software written in Java. The focus Danemark ; of ELKI is research in algorithms, with an emphasis on unsupervised methods in and outlier detection. Elsevier Text Enables the retrieval of highly Commercial Recherche Non https://www.elsevier.com/solutions/ Pays-Bas ; Mining specified information from unstructured d'informations ; professional-services/text-mining content, providing more meaningful Reconnaissance answers to complex research questions. d'entités nommées ; Extraction de relations ; Enju A deep syntactic parser for English Libre Parsing ; Oui http://www.nactem.ac.uk/enju/ Royaume- index.html Uni ; EnjuParser Enju is a syntactic parser for English Libre Parsing ; Oui http://pubannotation.org/annotators/ Japon ; EnjuParser Etuma Etuma text analysis service turns all your Commercial Classification ; Non http://www.etuma.com/home Finlande ; open-ended customer feedback into consistent and actionable information.

EventMine Event extraction system for biomedical Libre Extraction Non http://nactem.ac.uk/EventMine/ Royaume- text d’évènements ; Uni ;

Expernova Expernova utilise des algorithmes Commercial Apprentissage Non https://fr.expernova.com/ France ; sophistiqués, s’appuyant sur le Big Data automatique ; et le Machine Learning, pour connecter les réseaux d’innovation et dessiner un panorama global. Fastr Automatic indexing Libre Indexation ; Non https://perso.limsi.fr/jacquemi/ France ; FASTR/ FastText Library for efficient text classification and Libre Classification de Non https://fasttext.cc/ États-Unis ; representation learning textes ; Apprentissage prodond ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 16 Outil Description Licence Tâche(s) OMTD Source Pays

FreeLing An Open-Source Suite of Language Libre Reconnaissance Oui http://nlp.lsi.upc.edu/freeling/demo/ Espagne ; Analyzers d'entités nommées ; demo.php Annotation ; Galaxy Galaxy is an open, web-based platform Libre Architecture Oui https://galaxyproject.org/ États-Unis ; for accessible, reproducible, and logicielle ; transparent computational biomedical research. Gargantex A web platform to explore text-mining. Libre Textométrie ; Non https://gargantext.org/ France ;

GATE Suite of tools written in Java, used for Libre Tokenisation ; Oui https://gate.ac.uk/ Royaume- human language processing, analysis, Segmentation ; Uni ; and information extraction. Chunking ; Résolution de coréférence ; Reconnaissance d'entités nommées ; Sentence splitting ; Annotation ; Analyse morphologique ; PoS tagging ; Classification de textes ; Apprentissage automatique ; Genia tagger Part-of-speech tagging, shallow parsing, Libre PoS tagging ; Oui http://www.nactem.ac.uk/GENIA/ Royaume- and named entity recognition for Reconnaissance tagger/ Uni ; biomedical text d'entités nommées ; Parsing ; Gensim Scalable statistical semantics ; Analyze Libre Clustering ; Non https://radimrehurek.com/gensim/ République plain-text documents for semantic tchèque ; structure ; Retrieve semantically similar documents

Mise à jour du 25 mars 2019 Inist - F. Arnould | 17 Outil Description Licence Tâche(s) OMTD Source Pays

GibbsLDA GibbsLDA++ is a C/C++ implementation Libre Clustering ; Non http://gibbslda.sourceforge.net/ Japon ; of Latent Dirichlet Allocation (LDA) using Vietnam ; Gibbs Sampling technique for parameter estimation and inference. It is very fast and is designed to analyze hidden/latent topic structures of large-scale datasets including large collections of text/Web documents GLoVe GloVe is an unsupervised learning Libre Apprentissage Non https://nlp.stanford.edu/projects/ États-Unis ; algorithm for obtaining vector profond ; glove/ representations for words. Plongement de mots ; Glozz Plateforme d'annotation Libre Annotation ; Non http://www.glozz.org/ France ;

GNU PSPP GNU PSPP is a program for statistical Libre Non https://www.gnu.org/software/pspp/ ? analysis of sampled data Google Cloud L'API Google Cloud Natural Language Commercial Reconnaissance Non https://cloud.google.com/natural- États-Unis ; Natural révèle la structure et la signification des d'entités nommées ; language/ Language API textes grâce à des modèles de machine Analyse de learning puissants, dans une API REST sentiments ; Parsing conviviale. ; Classification ; Apprentissage profond ; Google L'API Prediction de Google propose des Commercial Classification ; Non https://cloud.google.com/prediction/ États-Unis ; Prediction API fonctionnalités de filtrage par motif et de machine learning.

Mise à jour du 25 mars 2019 Inist - F. Arnould | 18 Outil Description Licence Tâche(s) OMTD Source Pays

Heart of Gold Middleware architecture for the Libre Annotation ; Non http://heartofgold.dfki.de/ Allemagne ; integration of deep and shallow natural language processing components. It provides a uniform and flexible infrastructure for building applications that use Robust Minimal Recursion Semantics (RMRS) and/or general XML standoff annotation produced by natural language processing components. HunPos tagger Hunpos is an open source Libre PoS tagging ; Oui http://mokk.bme.hu/resources/ Hongrie ; reimplementation of TnT, the well known hunpos/ part-of-speech tagger by Thorsten Brants. Hyperbase Logiciel hypertexte pour le traitement Libre Textométrie ; Non http://bcl.cnrs.fr/article69? France ; documentaire et statistique des corpus Concordancier ; redirected_from=www%252eunice textuels Lemmatisation ; %252efr%252fbcl%252farticle69 Classification ; Clustering ; IBM SPSS Versatile data and text analytics Commercial Extraction Non http://www.spss.com.hk/software/ États-Unis ; Modeler workbench that helps you build accurate d'informations ; modeler/ predictive models quickly and intuitively, Reconnaissance without programming. d'entités nommées ; Extraction de relations ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 19 Outil Description Licence Tâche(s) OMTD Source Pays

IBM Watson Analyze text to extract meta-data from Commercial Extraction Non https://www.ibm.com/watson/ États-Unis ; Natural content such as concepts, entities, d'informations ; services/natural-language- Language keywords, categories, relations and Reconnaissance understanding/ Understanding semantic roles. Returns both overall d'entités nommées ; sentiment and emotion for a document, Extraction de and targeted sentiment and emotion relations ; towards keywords in the text for deeper Etiquetage de rôles analysis. sémantiques ; Analyse de sentiments ; Détection de la langue ; ILSP NLP Natural Language Processing services Libre PoS tagging ; Oui http://nlp.ilsp.gr/soaplab2-axis/ Grèce ; developed by the NLP group of the Lemmatisation ; Institute for Language and Speech Parsing ; Processing Chunking ; Sentence splitting ; Reconnaissance d'entités nommées ; Tokenisation ; ILSP NLP Web Natural Language Processing services Libre Parsing ; Oui http://nlp.ilsp.gr/soaplab2-axis/ Grèce ; Services developed by the NLP group of the Chuncking ; Institute for Language and Speech Lemmatisation ; Processing Reconnaissance d'entités nommées ;

Indico Text and image analysis to create Commercial Apprentissage Non https://indico.io/ États-Unis ; transformative tools. automatique ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 20 Outil Description Licence Tâche(s) OMTD Source Pays

Intellexer Based on the use of Natural Language Commercial Recherche Non https://www.intellexer.com/ États-Unis ; Processing and Machine Learning d'informations ; PoS products.html technologies, tools for text analytics tagging ; solutions that can be used as standalone Segmentation ; applications as well as integrated in the Parsing ; Extraction existing systems. de relations ; Analyse de sentiments ; Reconnaissance d'entités nommées ; Résumé automatique ; Q&A ; Classification ; Clustering ; Détection de la langue ; Vérification de l'orthographe ; Iramuteq Interface de pour les Analyses Libre Classification ; Non http://iramuteq.org/ France ; Multidimensionnelles de Textes et de Questionnaires. Java Automatic Java Automatic Term Extraction toolkit - a Libre Extraction Non https://code.google.com/archive/p/ Royaume- Term Extraction library of state-of-the-art term extraction terminologiques ; jatetoolkit/ Uni ; algorithms and framework for developing term extraction algorithms Jazzy Java Spell Check API Libre Vérification de Oui https://sourceforge.net/projects/ ? l'orthographe ; jazzy/ JCoRE The JULIE Lab Component Repository Libre Sentence Non http://julielab.github.io/ Allemagne ; (JCoRe) is an open software repository for segmentation ; full-scale natural language processing Tokenisation ; PoS based on the UIMA middleware tagging ; framework. Reconnaissance d'entités nommées ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 21 Outil Description Licence Tâche(s) OMTD Source Pays

Jubatus Online distributed machine learning on the Libre Classification ; Non http://jubat.us/en/overview.html Japon ; data streams of Big Data Clustering ; Analyse de régression ; KAF annotator Stand-alone application for annotating Libre Annotation ; Non http://kyoto-project.eu/ Europe ; KAF files with any set of tags to any level. xmlgroup.iit.cnr.it/kyoto/ Japon ; This annotator is used to create gold- index2091.html? standard data for evaluating the Kybot option=com_content&view=article&i output. d= KEA KEA is an algorithm for extracting Libre Extraction de mots Oui http://community.nzdl.org/kea/ Nouvelle- keyphrases from text documents. It can clés ; Zélande ; be either used for free indexing or for indexing with a controlled vocabulary. Keatext Keatext is an AI – driven text analytics Commercial Analyse de Non https://www.keatext.ai/ Canada ; technology that sentiments ; makes it easy for you to analyze large Analyse d'opinions ; volumes of unstructured customer feedback KEEL KEEL (Knowledge Extraction based on Libre Découverte de Non http://www.keel.es/ Espagne ; Evolutionary Learning) is an open source connaissances (GPLv3) Java software tool that can be used for a large number of different knowledge data discovery tasks.

KH coder KH Coder is a free software for Libre Clustering ; Non http://khc.sourceforge.net/en/ Japon ; quantitative content analysis or text Concordancier ; mining. It is also utilized for computational Réseau de co- linguistics. You can analyze Japanese, occurrences ; English, French, German, Italian, Portuguese and Spanish text with KH Coder. Also, Chinese (simplified), Korean and Russian language data can be analyzed with the latest Alpha release (Version 3).

Mise à jour du 25 mars 2019 Inist - F. Arnould | 22 Outil Description Licence Tâche(s) OMTD Source Pays

KIWI Keyword extractor Libre Extraction de mots Non http://www.quaero.org/ France ; clés ; module_technologique/kiwi- keyword-extractor/ KNIME Open source data analytics, reporting and Libre Apprentissage Non https://www.knime.com/ Suisse ; integration platform. automatique ; KnowledgeREA Integrated customer intelligence by Commercial Analyse de Non http://www.angoss.com/ Canada ; DER combining visual text discovery and sentiments ; sentiment analysis with the power of predictive analytics LanguageComp Understanding the information stored in Commercial Reconnaissance Non http://www.languagecomputer.com/ États-Unis ; uter (Cicero, any large collections of text. d'entités nommées ; Ferret) Résolution de coréférence ; Annotation ; Extraction de relations ; Extraction d'évènements ; Q&A ; LAPPS Grid An open, interoperable web service Libre Architecture Non http://www.lappsgrid.org/ États-Unis ; platform for natural language processing logicielle ; (NLP) research and development Tokenisation ; Reconnaissance d'entités nommées ; PoS tagging ; Sentence splitting ; Parsing ; Chunking ;

Lavastorm Visual data discovery solution Libre Prétraitement ; Non http://www.lavastorm.com/ États-Unis ; analytics engine

Mise à jour du 25 mars 2019 Inist - F. Arnould | 23 Outil Description Licence Tâche(s) OMTD Source Pays

Le Trameur Le Trameur est un programme d’analyse Libre Textométrie ; Non http://www.tal.univ-paris3.fr/ France ; comportant de nombreuses Annotation trameur/#p4 fonctionnalités pour l’analyse automatique, statistique et documentaire de textes en vue de leur profilage sémantique, thématique et de leur interprétation. Ce logiciel est à l’origine un outil de textométrie : il intègre les fonctionnalités classiques de ce type d’outils dans ce domaine. Il dispose aussi des fonctionnalités particulières qui permettent d’annoter dynamiquement des corpus ou d’explorer des ressources richement annotées (treebanks monolingues/multilingues ou des alignements). Lexalytics Natural language processing Commercial PoS tagging ; Non https://www.lexalytics.com/ États-Unis ; (Semantria) Extraction de relations ; Classification ; Tokenisation ; Extraction de relations ; Analyse d'opinions ; Analyse de sentiments ; Résolution d'anaphore ; Racinisation ; Reconnaissance d'entités nommées ; Lexi-co Analyses textometriques Libre Textométrie ; Non http://www.lexi-co.com/index.html France ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 24 Outil Description Licence Tâche(s) OMTD Source Pays

Leximancer Leximancer automatically analyses your Commercial Extraction Non https://info.leximancer.com/ États-Unis ; text documents to identify the high level d'informations ; concepts in your text documents, delivering the key ideas and actionable insights you need with powerful interactive visualisations and data exports. Liblinear Library for large linear classification Libre Classification ; Non http://www.csie.ntu.edu.tw/~cjlin/ Taïwan ; liblinear/ LIBSVM Library for support vector machine Libre Classification ; Oui http://www.csie.ntu.edu.tw/~cjlin/ Taïwan ; libsvm/ LingPipe LingPipe is tool kit for processing text Libre/ Reconnaissance Oui http://alias-i.com/lingpipe/index.html États-Unis ; using computational linguistics. Commercial d'entités nommées ; Détection de la langue ; Classification ; Sentence splitting ; Tokenisation ; PoS tagging ; Linguistic LIWC2015 is the gold standard in Commercial Annotation ; Non http://liwc.wpengine.com/ États-Unis ; Inquiry Word computerized text analysis. Learn how the Classification ; Count words we use in everyday language reveal our thoughts, feelings, personality, and motivations.

LIONoso Integrated tool for Machine Learning and Commercial Apprentissage Non http://lionoso.com/ Italie ; Intelligent Optimization automatique ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 25 Outil Description Licence Tâche(s) OMTD Source Pays

LPU LPU (which stands for Learning from Libre Classification ; Non https://www.cs.uic.edu/~liub/LPU/ États-Unis ; Positive and Unlabeled data) is a text LPU-download.html learning or classification system that learns from a set of positive documents and a set of unlabeled documents (without labeled negative documents). This type of learning is different from classic text learning/classification, in which both positive and negative training documents are required. Luminoso Understand, measure and act on large Commercial Apprentissage Non https://luminoso.com/ États-Unis ; amounts of unstructured text. automatique ; Classification ; Analyse de tendances ; Magaputer Data and text mining solutions Commercial Classification ; Non http://megaputer.com/site/index.php États-Unis ; Clustering ; Analyse de régression ; Reconnaissance d'entités nommées ; Extraction de relations ; Détection de la langue ; PoS tagging ; Extraction de mots clés ; Parsing ; Analyse de sentiments ; Résolution d'anaphore ; MALLET MALLET is a Java-based package for Libre Clustering ; Oui http://mallet.cs.umass.edu/ États-Unis ; statistical natural language processing, Classification ; document classification, clustering, topic modeling, information extraction, and other machine learning applications to text.

Mise à jour du 25 mars 2019 Inist - F. Arnould | 26 Outil Description Licence Tâche(s) OMTD Source Pays

MaltParser MaltParser is a system for data-driven Libre Parsing ; Oui http://www.maltparser.org/ Suède ; dependency parsing, which can be used to induce a parsing model from treebank data and to parse new data using an induced model Massive Online Open source framework for data stream Libre Clustering ; Non https://moa.cms.waikato.ac.nz/ Nouvelle- Analysis (MOA) mining Classification ; Zélande ; Analyse de régression ; MATE Multilevel Annotation, Tools Engineering Libre Annotation ; Oui http://xml.coverpages.org/mate.html Royaume- Uni ; Allemagne ; Danemark ; MatheoSoftware Patents search and analysis, Commercial Recherche Non https://www.matheo-software.com/ France ; technological trends, data analysis d'informations ; Analyse de tendances ; MATLAB Analyse de données, développement Commercial Clustering ; Non https://fr.mathworks.com/? États-Unis ; d'algorithmes et création de modèles Classification ; s_tid=gn_logo mathématiques, deep learning Analyse de régression ; Apprentissage profond ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 27 Outil Description Licence Tâche(s) OMTD Source Pays

Meaning Cloud Extract the meaning of all kind of Libre/ Analyse de Non https://www.meaningcloud.com/ États-Unis ; unstructured content: social conversation, Commercial sentiments ; articles, documents... Analyse de tendance ; Clustering ; Classification de textes ; Résumé automatique ; Détection de la langue ; Lemmatisation ; PoS tagging ; Etiquetage morphosyntaxique ; Meaning Cloud Way to extract the meaning of all kind of Libre/ Analyse de Non https://www.meaningcloud.com États-Unis ; unstructured content: social conversation, Commercial sentiment ; articles, documents... Classification de textes ; Clustering de textes ; Catégorisation ; Résumé automatique ; Reconnaissance d'entités nommées ; MeCab Libre Parsing ; Oui https://taku910.github.io/mecab/ Japon ; libmecab.html MER Minimal name entity recognizer Libre Reconnaissance Non https://github.com/lasigeBioTM/ Portugal ; d'entités nommées ; MER MetaMAp Tool for recognizing UMLS concepts in Libre Annotation ; Non https://metamap.nlm.nih.gov/ États-Unis ; texts

Mise à jour du 25 mars 2019 Inist - F. Arnould | 28 Outil Description Licence Tâche(s) OMTD Source Pays

MicroFocus Big Data and analytics software Commercial Recherche Non https://software.microfocus.com/en- Royaune- d'informations ; us/software/big-data-analytics- Uni ; Découverte de software connaissances ; Apprentissage automatique ; Microsoft Azure Détectez le sentiment, les phrases clés, Commercial Analyse de Non https://azure.microsoft.com/fr-fr/ États-Unis ; les sujets et la langue du texte sentiments ; services/cognitive-services/text- Extraction de mots analytics/ clés ; Détection de la langue ; Annotation sémantique ; Microsoft The Microsoft Cognitive Toolkit (CNTK) is Libre Apprentissage Non https://docs.microsoft.com/en-us/ États-Unis ; Cognitive an open-source toolkit for commercial- profond ; cognitive-toolkit/ ToolKit grade distributed deep learning. It describes neural networks as a series of computational steps via a directed graph. CNTK allows the user to easily realize and combine popular model types such as feed-forward DNNs, convolutional neural networks (CNNs) and recurrent neural networks (RNNs/LSTMs). CNTK implements stochastic gradient descent (SGD, error backpropagation) learning with automatic differentiation and parallelization across multiple GPUs and servers.

Mise à jour du 25 mars 2019 Inist - F. Arnould | 29 Outil Description Licence Tâche(s) OMTD Source Pays

Microsoft Distributed machine learning has become Libre ? Topic modeling ; Non http://www.dmtk.io/index.html États-Unis ; Distributed more important than ever in this big data Apprentissage Machine era. Especially in recent years, practices automatique ; Learning Toolkit have demonstrated the trend that more Apprentissage training data and bigger models tend to profond generate better accuracies in various applications. However, it remains a challenge for common machine learning researchers and practitioners to learn big models from huge amount of data, because the task usually requires a large number of computation resources. In order to tackle this challenge, we release the Microsoft Distributed Machine Learning Toolkit (DMTK), which contains both algorithmic and system innovations. Microsoft SQL Ensemble d'outils pour la fouille de ? Classification ; Non https://docs.microsoft.com/en-us/ États-Unis ; Server Analysis données Clustering ; Anayse sql/analysis-services/data-mining/ Services de régression ; data-mining-tools MiningMart Prétraitement des données Libre Prétraitement ; Non http://mmart.cs.uni-dortmund.de/ Allemagne ; research/index.html MiniPar Libre Parsing ; Oui https://webdocs.cs.ualberta.ca/ Canada ; ~lindek/minipar.htm ML-Flex an open-source software package Libre Classification ; Non http://mlflex.sourceforge.net/ États-Unis ; designed to enable flexible and efficient processing of disparate data sets for machine-learning (classification) analyses

MLPACK Scalable machine learning library, written Libre Classification ; Non http://mlpack.org/ États-Unis ; in C++ Clustering ; Analyse de régression ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 30 Outil Description Licence Tâche(s) OMTD Source Pays

mlpy mlpy provides a wide range of state-of- Libre Classification ; Non http://mlpy.sourceforge.net/ Italie ; the-art machine learning methods for Clustering ; supervised and unsupervised. Modalisa Création de questionnaires en ligne ou Commercial Classification Non https://modalisa.com/logiciel/ France ; papier, diffusion et recueil de données, modalisa.php transformation de variables, codification de textes, analyses univariées et multivariées, indicateurs spécifiques, régressions, rapports dynamiques exportables sous PowerPoint, export et import des données sous format Excel et Texte... Modular toolkit Modular toolkit for Data Processing (MDP) Libre Classification ; Non https://pypi.python.org/pypi/MDP/ États-Unis ; for Data is a library of widely used data processing Clustering ; 2.4 Allemagne ; Processing algorithms that can be combined according to a pipeline analogy to build more complex data processing software. Monkeylearn Text Analysis with machine learning Libre/ Reconnaissance Non https://monkeylearn.com/ États-Unis ; commercial d'entités nommées ; Analyse de sentiments ; Extraction de topics ; Apprentissage automatique ; Prétraitement ; MorphAdoerner MorphAdorner is a Java command-line Libre Tokenisation ; Non http:// États-Unis ; program which acts as a pipeline PoS tagging ; morphadorner.northwestern.edu/ manager for processes performing Reconnaissance morphadorner/ morphological adornment of words in a d'entités nommées ; text Sentence splitting ; Lemmatisation ; Annotation ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 31 Outil Description Licence Tâche(s) OMTD Source Pays

MutationFinder MutationFinder is a biomedical natural Libre Extraction Oui https://sourceforge.net/projects/ États-Unis ; language processing (NLP) system for d'informations ; mutationfinder/ extracting mentions of point mutations from free text. MutationFinder achieves high performance (99% precision, 81% recall on blind test data) as an information extraction system mutext Analytics and decision science solutions. Commercial Parsing ; Non https://www.mu-sigma.com/ Inde ; Classification de textes ; Clustering ; MXNet A flexible and efficient library for deep Libre Apprentissage Non https://mxnet.incubator.apache.org États-Unis ; learning profond ; NaCTeM The National Centre for Text Mining bases Libre Reconnaissance Oui http://nactem.ac.uk/software.php Royaume- Software Tools its service systems on a number of text d'entités nommées ; Uni ; mining software tools. PoS tagging ; Parsing ; Sentencfe splitting ; Paragraph splitting ; Extraction d'évènements ; Annotation ; Narrative Quill transforms data into automated, Commercial Génération de Non https://narrativescience.com/ États-Unis ; Science Quill human-sounding Intelligent Narratives langage naturel ; that empower your people with insights to improve every aspect of your business.

Mise à jour du 25 mars 2019 Inist - F. Arnould | 32 Outil Description Licence Tâche(s) OMTD Source Pays

NaturalText For Life sciences: NaturalText's Machine Commercial Extraction Non http://naturaltext.com/ Inde ; Learning Algorithms can process d'informations ; Scientific Papers, Bio Sequences to find Extraction de patterns and help scientists, researchers relations ; to advance their research. For financial Apprentissage sector : NaturalText's Machine Learning automatique ; Algorithms can combine various data Découverte de formats, cross verify for incorrect connaissances ; information, help companies to know more from the data NCBI Text Ensemble de applications web ou de Libre Annotation ; Non https://www.ncbi.nlm.nih.gov/ États-Unis ; Mining Tools bureau pour la fouille de textes dans le Recherche research/bionlp/Tools/ domaine biomédical d'informations ; Reconnaissance d'entités nommées ; Normalisation ; Désambiguisation ;

NERD Named entity recognition and Libre Reconnaissance Non http://nerd.eurecom.fr/ France ; desambiguation d'entités nommées ; NERSuite Named Entity Recognition toolkit Libre Reconnaissance Non http://nersuite.nlplab.org/ Japon ; d'entités nommées ; Netowl Text and Entity Analytics Products Commercial Reconnaissance Non https://www.netowl.com/ États-Unis ; d'entités nommées ; Analyse de sentiments ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 33 Outil Description Licence Tâche(s) OMTD Source Pays

Neural designer Neural Designer is a software tool for Libre/ Apprentissage Non https://www.neuraldesigner.com/ Espagne ; advanced analytics. It includes tools for commercial automatique ; descriptive, diagnostic, predictive and prescriptive analytics. It allows you to get actionable insights resulting in smarter decisions and better business outcomes. Neural networks are the most powerful method to discover intricate relationships, recognize complex patterns or predict current trends in your data. NeuroNER A Named-Entity Recognition program Libre Reconnaissance Non http://neuroner.com/ États-Unis ; based on neural networks d'entités nommées ; NLTK Platform for building Python programs to Libre Parsing ; Chunking ; Non http://www.nltk.org/ États-Unis ; work with human language data Concordiancier ; Classification ; Clustering ; Extraction de relations sémantiques ; Anlyse de sentiments ; Racinisation ; Tokenisation ; Traduction automatique ;

NooJ Linguistic development environment Libre Annotation ; Non http://www.nooj4nlp.net/ France ; software as well as a corpus processor. Noopsis Noopsis automatise la collecte Commercial Recherche Non http://www.noopsis.fr/index.fr.html France ; d'informations stratégiques par la fouille d'informations ; de documents textuels. Analyse sémantique ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 34 Outil Description Licence Tâche(s) OMTD Source Pays

ntent Semantic search technology to determine Commercial Recherche Non http://www.ntent.com/ États-Unis ; user intent and the contextual meaning of d'informations ; words Reconnaissance d'entités nommées ; Détection de la langue ; Classification ; Lemmatisation ; Toklenisation ; Extraction d'informations ; Apprentissage automatique ; Nvivo NVivo est un logiciel qui supporte des Commercial Classification ; Non http://www.qsrinternational.com/ Australie ; méthodes de recherches qualitatives et Visualisation nvivo-french combinées. Il est conçu pour vous permettre d'organiser, analyser et trouver du contenu perspicace parmi des données non structurées ou qualitatives telles que des interviews, des réponses libres obtenues dans le cadre d'un sondage, des articles, des médias sociaux et des pages Web. Odintext Text analytics software Commercial Analyse de Non http://odintext.com/ États-Unis ; sentiments ; Apprentissage automatique ; OntoText Ontotext provides a complete set of Commercial Annotation Non https://ontotext.com/ Bulgarie ; Semantic Technology enabling better sémantique ; content management, knowledge Extraction de discovery and semantic search. relations ; Désambiguisation ; Apprentissage automatique ; Classification ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 35 Outil Description Licence Tâche(s) OMTD Source Pays

Open Calais Way to tag the people, places, Commercial Annotation ; Oui http://www.opencalais.com/about- États-Unis ; companies, facts, and events in your Reconnaissance open-calais/ content to increase its value, accessibility d'entités nommées ; and interoperability. Extraction de relations ; Extraction d'évènements ; Clustering ; Open semantic Free Software for your own Search Libre Recherche Non https:// Allemagne ; search Engine, Explorer for Discovery of large d'informations ; www.opensemanticsearch.org/ document collections, Media Monitoring, Annotation ; Text Analytics, Document Analysis & Text Mining platform based on Apache Solr or Elasticsearch open-source enterprise- search and Open Standards for Linked Data, Semantic Web & Linked Open Data integration OpenCCG OpenCCG, the OpenNLP CCG Library, is Libre Parsing ; PoS Oui http://openccg.sourceforge.net/ États-Unis ; an open source natural language tagging ; processing library written in Java, which provides parsing and realization services based on Mark Steedman's Combinatory Categorial Grammar (CCG) formalism OpenMinTED OpenMinted sets out to create an open, Libre http://openminted.eu/ Europe service-oriented e-Infrastructure for Text and Data Mining (TDM) of scientific and scholarly content. Researchers can collaboratively create, discover, share and re-use Knowledge from a wide range of text-based scientific related sources in a seamless way

Mise à jour du 25 mars 2019 Inist - F. Arnould | 36 Outil Description Licence Tâche(s) OMTD Source Pays

OpenNER OpeNER’s main goal is to provide a set of Libre Reconnaissance Non https://www.opener-project.eu/ Italie ; ready to use tools to perform some d'entités nommées ; index.html Espagne ; natural language processing tasks, free Analyse de Pays Bas ; and easy to adapt for Academia, sentiment ; Analyse Research and Small and Medium d’opinion Enterprise to integrate them in their workflow. More precisely, OpeNER aims to be able to detect and disambiguate entity mentions and perform sentiment analysis and opinion detection on the texts, to be able for example, to extract the sentiment and the opinion of customers about certain resource (e.g. hotels and accommodations) in Web reviews. OpenNN OpenNN is an open source class library Libre Apprentissage Non http://www.opennn.net/ Espagne ; written in C++ programming language profond ; which implements neural networks, a main area of machine learning research. OpenRefine Nettoyage, mise en forme et Libre Prétraitement ; Non http://openrefine.org/ États-Unis ; transformation de données OpenText Digitize processes and discover the value Commercial Recherche Non http://www.opentext.com/ Canada ; in information using analytics and Artificial d'informations ; Intelligence. Classification ; Oracle Data Oracle Data Mining (ODM), a component Commercial Classification ; Non http://www.oracle.com/technetwork/ États-Unis ; Mining of the Oracle Advanced Analytics Clustering ; Analyse database/options/advanced- Database Option, provides powerful data de régression ; analytics/odm/overview/index.html mining algorithms that enable data Détection analytsts to discover insights, make d'anomalies ; Règle predictions and leverage their Oracle data d'associations ; and investment.

Mise à jour du 25 mars 2019 Inist - F. Arnould | 37 Outil Description Licence Tâche(s) OMTD Source Pays

Orange Data Open source machine learning and data Libre Clustering ; Non https://orange.biolab.si/ Slovénie ; Mining Toolbox visualization for novice and expert. Classification ; Analyse de régression ; Overview Overview is a document mining Libre Clustering ; Non https://www.overviewdocs.com/ ? application originally built for investigative Recherche journalists. It’s also used for legal work, d'informations ; training machine learning models, and Annotation ; research of all types. It’s a visualization Reconnaissance and analysis tool designed for sets of d'entités nommées ; documents, from dozens to millions of pages of materia Pagelyser Pagelyzer is a tool which compares two Libre Analyse de pages Non http:// France ; web pages versions and decides if they web ; pagelyzer.openpreservation.org/ are similar or not. PANDAS Library providing high performance, Libre Analyse de Non http://pandas.pydata.org/ États-Unis ; easey-to-use data structure and data régression ; analysis tools for the Python programming language Pattern Pattern is a web mining module for the Libre PoS tagging ; Non https://www.clips.uantwerpen.be/ Pays-Bas ; Python programming language. Analyse de pages/pattern sentiments ; Apprentissage automatique ; n- gram ; Clustering ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 38 Outil Description Licence Tâche(s) OMTD Source Pays

Penelope Penelope is a cloud-based, open and Tokenisation ; https://penelope.vub.be Europe ; modular platform that consists of tools Lemmatisation ; and techniques for mapping landscapes Chunking ; PoS of opinions expressed in online (social) tagging ; media. The platform is used for analysing Reconnaissance the opinions that dominate the debate on d’entités nommées ; certain crucial social issues, such as Analyse syntaxique immigration, climate change and national de dépendance ; identity. apprentissage automatique ; plongement lexical ; Sentencisation ; Philologic PhiloLogic™ is the primary full-text Libre Recherche Non https://sites.google.com/site/ États-Unis ; search, retrieval and analysis tool d’information ; philologic3/home developed by the ARTFL Project and the Digital Library Development Center (DLDC) at the University of Chicago. This is a Free Software implementation of PhiloLogic for large TEI-Lite document collections. Pingar Pingar DiscoveryOne Content Enrichment Commercial Classification de Non http://pingar.com/ États-Unis ; automatically tags and categorizes textes ; Recherche content. Typically, it is used to improve d'informations ; findability of information in an Electronic Découverte de Content Management System (ECMS) by connaissances ; enabling faceted search. PlaidML Framework for making deep learning work Libre Apprentissage Non https://github.com/plaidml/plaidml ? everywhere profond ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 39 Outil Description Licence Tâche(s) OMTD Source Pays

PoolParty PoolParty is a world-class semantic Commercial Reconnaissance Non https://www.poolparty.biz/ Autriche ; Semantic Suite technology suite that offers sharply d'entités nommées ; focused solutions to knowledge Annotation ; organization and content business. Recherche d'informations ; Extraction de relations ; Extraction terminologique ; Classification de textes ; PrediCX Automated Text Analytics for Voice of Commercial Apprentissage Non https://warwickanalytics.com/ Royaume- Customer (VoC) data, chatbots, service automatique ; predicx/ Uni ; desks, complaint handling, call center Analyse de automation and early warning of issues. sentiments ; Quick and Easy to Deploy, High-Impact, AI and Machine Learning for Text Analysis. Prosuite ProSuite is an integrated collection of Commercial Clustering ; Non https://provalisresearch.com/ Canada ; Provalis Research text analytics tools that Concordancier ; products/prosuite/ allow one to explore, analyze and relate Annotation ; both structured and unstructured data. Analyse de Provalis Research Text Analytics Software tendances ; allows one to perform advanced Extraction de mots computer assisted qualitative coding on clés ; Classification documents and images using QDA Miner, de textes ; to apply the powerful content analysis and text mining features of WordStat on textual data, and to perform advanced statistical analysis on numerical and categorical data using SimStat

Mise à jour du 25 mars 2019 Inist - F. Arnould | 40 Outil Description Licence Tâche(s) OMTD Source Pays

Proxem Studio Transforme les données textuelles en Commercial Classification de Non https://www.proxem.com/ France ; prise de decision textes ; Recherche d'informations ; Découverte de connaissances ; Annotation ; Analyse de sentiments ; PubTator PubTator is a Web-based tool for Libre Annotation ; Oui https://www.ncbi.nlm.nih.gov/ États-Unis ; accelerating manual literature curation. CBBresearch/Lu/Demo/PubTator/ index.cgi?user=User284144660 PyTorch PyTorch is a deep learning framework for Libre Apprentissage Non https://pytorch.org/ États-Unis ; fast, flexible experimentation. profond ; France ; Qlucore Omics Identify patterns and structure when Commercial Classification ; Non https://www.qlucore.com/ Suède ; Explorer exploring biological data Clustering ; QWAM Solutions logicielles métier répondant aux Commercial Extraction Non http://www.qwamci.com/ France ; besoins de gestion des flux d'information d'informations ; (documentaire, textuelle, multimedia), de moteur de recherche, de veille et d'analyse et d'enrichissement sémantique

R Free software environment for statistical Libre Tokenisation ; Non https://www.r-project.org/ Nouvelle- computing and graphics. Racinisation ; PoS Zélande ; tagging ; Parsing ; Canada ; Reconnaissance d'entités nommées ; Analyse de sentiments ; Classification ; Clustering ; Apprentissage profond ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 41 Outil Description Licence Tâche(s) OMTD Source Pays

R.TeMIS Environnement graphique de travail sous Libre Racinisation ; Non http://rtemis.hypotheses.org/ France R permettant de créer, manipuler et Chunking ; analyser des corpus de textes. Clustering ; RapidMiner RapidMiner is code free data science Libre/ Tokenisation ; Non https://rapidminer.com/ Allemagne ; platform that unifies data prep, machine commercial Racinisation ; learning, and model deployment. Reconnaissance d'entités nommées ; Analyse de sentiments ; Classification ; Clustering ; Rasp The RASP system includes state-of-the- Libre/ Tokenisation ; Oui https://www.ilexir.co.uk/rasp/ Royaume- art modules for finding sentence commercial Lemmatisation ; index.html Uni ; boundaries, finding individual words, PoS tagging ; analyzing words to identify the word root Parsing ; and any suffixes, assigning part-of- speech labels to words in running text, and analyzing the grammatical relations between words and larger units within sentences. Rattle GUI for data mining using R Libre Classification ; Non https://rattle.togaware.com/ États-Unis ; Clustering ; RepKnight Software platform provides real-time Commercial Recherche Non https://www.repknight.com/ Royaume- cyber intelligence to keep people, d'informations ; Uni ; companies and assets safe from internal and external threats

Resoomer Résumé automatique Libre/ Résumé Non https://resoomer.com France ; Commercial automatique Rocket Folio Automated content search and publishing Commercial Recherche Non http://www.rocketsoftware.com/ États-Unis ; for desktop, digital media, web, or d'informations ; products/rocket-folionxt intranet

Mise à jour du 25 mars 2019 Inist - F. Arnould | 42 Outil Description Licence Tâche(s) OMTD Source Pays

Rosetta ROSETTA is a toolkit for analyzing tabular Libre Découverte de Non http://bioinf.icm.uu.se/rosetta/ Suède ; data within the framework of rough set connaissances ; theory. ROSETTA is designed to support the overall data mining and knowledge discovery process: From initial browsing and preprocessing of the data, via computation of minimal attribute sets and generation of if-then rules or descriptive patterns, to validation and analysis of the induced rules or patterns. Rosette Text Multilingual Text Analytics Solution Commercial Classification de Non https://www.rosette.com/ États-Unis ; Analytics textes ; Clustering ; Analyse de sentiments ; Reconnaissance d'entités nommées ; Entity linking ; Extraction de relations ; Détection de la langue ; Traduction automatique ; Tokenisation ; PoS tagging ; Lemmatisation ; SANSA SANSA is a big data processing engine Libre Classification ; Non http://sansa-stack.net/ Allemagne for scalable processing of large-scale RDF Clustering ; data. SANSA uses Spark and Flink which Règlesd'association offer fault-tolerant, highly available and ; Détection scalable approaches to process massive d'anomalie ; sized datasets efficiently. SANSA provides the facilities for Semantic data representation, Querying, Inference, and Analytics

Mise à jour du 25 mars 2019 Inist - F. Arnould | 43 Outil Description Licence Tâche(s) OMTD Source Pays

SAP predictive Predictive modeling suite Commercial https://www.sap.com/products/ Allemagne analytics analytics/predictive-analytics.html SAS Enterprise Create accurate predictive and descriptive Commercial Prétraitement ; Non https://www.sas.com/en_id/ États-Unis ; Mining models for large volumes of data. Apprentissage software/analytics/enterprise- automatique ; miner.html SAS Text Miner Text mining software from SAS Commercial Découverte de Non https://www.sas.com/en_us/ États-Unis ; automatically finds information buried in connaissances ; software/text-miner.html unstructured text data. Reconnaissance d'entités nommées ; Clustering ; Extraction de relations ; Apprentissage automatique ; Scikit-learn Simple and efficient tools for data mining Libre Classification ; Non http://scikit-learn.org/stable/ France ; and data analysis. Accessible to Clustering ; index.html everybody, and reusable in various Analyse de contexts. Built on NumPy, SciPy, and régression ; matplotlib Scrapy An open source and collaborative Libre Indexation ; Non https://scrapy.org ? framework for extracting the data you need from websites. In a fast, simple, yet extensible way.

SDL MultiTerm Computer assisted translation Commercial Traduction Non https://www.sdltrados.com/ Allemagne ; Extract automatique ; Semdee Comprendre et exploiter de gros volumes Commercial Apprentissage Non http://www.semdee.com/ France ; de données textuelles automatique ; SemRep SemRep is a UMLS-based program that Libre Extraction de Non https://semrep.nlm.nih.gov/ États-Unis ; extracts three-part propositions, called relations semantic predications, from sentences in biomedical text.

Mise à jour du 25 mars 2019 Inist - F. Arnould | 44 Outil Description Licence Tâche(s) OMTD Source Pays

SENNA ENNA is a software distributed under a Libre PoS tagging ; Non http://ronan.collobert.com/senna/ États-Unis ; non-commercial license, which outputs a Chunking ; host of Natural Language Processing Reconnaissance (NLP) predictions: part-of-speech (POS) d'entités nommées ; tags, chunking (CHK), name entity Etiquetage de rôle recognition (NER), semantic role labeling sémantique ; (SRL) and syntactic parsing (PSG). Parsing ; Sentic API Sentic API provides the semantics and Libre Analyse de Non http://sentic.net/api/ États-Unis ; sentics (i.e., the denotative and sentiments ; connotative information) associated with the concepts of SenticNet 4, a semantic network of commonsense knowledge that contains 50,000 nodes (words and multiword expressions) and thousands of connections (relationships between nodes). SentiStrength SentiStrength estimates the strength of Libre Analyse de Non http://sentistrength.wlv.ac.uk/ Royaume- positive and negative sentiment in short sentiments ; Uni ; texts, even for informal language Shogun The Shogun Machine learning toolbox Libre Non http://shogun-toolbox.org/ ? offers a wide range of efficient and unified Machine Learning methods. Simple Software application oriented to Commercial Extraction Non http://www.dail-software.com/help/ Espagne ; Extractor extracting terminology from texts. Some terminologique ; 9_en/index.html of its main features are its simple use and its intuitive interfaces. This tool allows the setting of different extraction criteria and exporting files.

Sisense Business intelligence tool for simplifying Commercial Prétraitement ; Non https://www.sisense.com/get/ États-Unis ; complex data preparation and analysis. Apprentissage pricing/ Israël ; automatique ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 45 Outil Description Licence Tâche(s) OMTD Source Pays

Sketch Engine Sketch Engine is the ultimate tool to Commercial Collocation ; Non https://www.sketchengine.eu République explore how language works. Its Concordancier ; tchèque ; algorithms analyze authentic texts of Extraction billions of words (text corpora) to identify terminologique ; instantly what is typical in language and what is rare, unusual or emerging usage. It is also designed for text analysis or text mining applications SMART Text The SMART Text Miner is a sophisticated ? Extraction Non http://www.smartny.com/miner.htm États-Unis ; Miner software tool that can extract hidden terminologique ; knowledge from legacy texts. Smartlogic Semantic platform that allows Commercial Découverte de Non https://www.smartlogic.com/ États-Unis ; organizations to realize the business value connaissances ; of their information. By leveraging a Reconnaissances common vocabulary and sophisticated d'entités nommées ; semantic techniques Semaphore: Extraction de relations ; Classification ; Recherche d'informations ; Désambiguisation ; SoftLaw Analyse de documents juridiques Commercial Extraction Non https://www.softlaw.digital/ France ; d'informations ; SpaCy Software library for NLP. Libre Apprentissage Non https://spacy.io/ Australie ; profond ; Tokenisation ; PoS tagging ; Segmentation de phrases ; Parsing ; Reconnaissance d'entités nommées ; classification de textes ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 46 Outil Description Licence Tâche(s) OMTD Source Pays

Stanbold Set of reusable components for semantic Libre Détection de la Non https://stanbol.apache.org États-Unis ; content management. langue ; Tokenisation ; PoS tagging ; Chunking ; Lemmatisation ; Reconnaissance d'entités nommées ; Stanford NLP An integrated suite of natural language Libre PoS Tagging ; Oui https://nlp.stanford.edu/ États-Unis ; processing tools for English and Résolution de (mainland) Chinese, including coréférence ; tokenization, part-of-speech tagging, Tokenisation ; named entity recognition, parsing, and Reconnaissance coreference. d'entités nommées; Parsing ; Extraction de relations ; Classification ; Stanford Topic The Stanford Topic Modeling Toolbox Libre Clustering ; Topic Non https://nlp.stanford.edu/software/ États-Unis ; Modeling (TMT) brings topic modeling tools to modeling ; tmt/tmt-0.4/ Toolbox social scientists and others who wish to perform analysis on datasets that have a substantial textual component Text Statistica Text Miner is an optional Commercial Lemmatisation ; Non https://www.statsoft.fr/logiciels/ États-Unis ; Miner extension of Statistica Data Miner, ideal Clustering ; textminer.php for translating unstructured text data into meaningful, valuable clusters of decision- making "gold." Stratifyd Stratifyd's data analytics platform allows Commercial Clustering ; Analyse Non https://www.stratifyd.com/ États-Unis ; users to integrate, analyze, and visualize de sentiments ; data in a single platform, empowering Extraction analysts through a holistic view of both d'nformations ; structured and unstructured data.

Mise à jour du 25 mars 2019 Inist - F. Arnould | 47 Outil Description Licence Tâche(s) OMTD Source Pays

streamDM streamDM is a new open source software Libre Classification ; Non http://huawei-noah.github.io/ Chine ; for mining big data streams using Spark Clustering ; streamDM/ Streaming Analyse de régression ; Synaptica Software solution for knowledge Commercial Annotation ; Non http://www.synaptica.com/ États-Unis ; organization and discovery. Classification ; Sysomos Sysomos is a unified, insights-driven Commercial Recherche Non https://sysomos.com/ Canada ; social platform that gives marketers the d'informations ; easiest way to Search, Discover, Listen, Découverte de Publish, Engage, and Analyze at scale connaissances ; across earned, owned, and paid media. Systran Understanding, analyze and act in over 50 Commercial Analyse de Non http://www.systran.io/ Corée du languages sentiments ; Sud ; Traduction automatique ; Reconnaissance d'entités nommées ; Détection de la langue ; Segmentation ; Tokenisation ; PoS tagging ; Analyse morphologique ; TACIT Text Analysis,Crawling and Interpretation Libre Classification de Non http://tacit.usc.edu/ États-Unis ; Tool textes ; Clustering ;

Tagtog Biomedical annotation tool Libre Annotation ; Non https://www.tagtog.net/ Pologne ;

TAMS TAMS stands for Text Analysis Markup Libre identification de Non http://tamsys.sourceforge.net États-Unis ; System. It is a convention for identifying thèmes themes in texts (web pages, interviews, field notes). It was designed for use in ethnographic and discourse research.

Mise à jour du 25 mars 2019 Inist - F. Arnould | 48 Outil Description Licence Tâche(s) OMTD Source Pays

TANAGRA TANAGRA is a free DATA MINING Libre Apprentissage Non https://eric.univ-lyon2.fr/~ricco/ France ; software for academic and research automatique ; tanagra/en/tanagra.html purposes. It proposes several data mining methods from exploratory data analysis, statistical learning, machine learning and databases area. TapoRware TAPoRware is a set of text analysis tools Libre Concordancier ; Non http://taporware.ualberta.ca/ Canada ; that enables users to perform text Tokenisation ; ~taporware/about.shtml analysis on HTML, XML and plain text Extraction de liens ; files, using documents from the users' Résumé machine or on the web. automatique ; TensorFlow Machine learning library Libre Apprentissage Non https://www.tensorflow.org/ États-Unis ; automatique ; Termsuite Outil d'extraction terminologique et Libre Extraction Oui https://termsuite.github.io/fr/ France ; d'alignment multilingue de termes. terminologique ; Text2data Advanced text analytics Commercial Analyse de Non http://text2data.org/ ? sentiments ; Résumé automatique ; Classification de textes ; Reconnaissance d'entités nommées ; Clustering ; Extraction de mots clés ;

Textalytics Textalytics is a meaning extraction service Commercial Annotation ; Oui https://textalytics.io/ ? that produces meaningful data from social PoS tagging ; media content, contracts, news, and other Parsing ; documents Lemmatisation ; Analyse de sentiments ; Clustering ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 49 Outil Description Licence Tâche(s) OMTD Source Pays

Textblob TextBlob is a Python (2 and 3) library for Libre Extraction Non https://textblob.readthedocs.io/en/ États-Unis ; processing textual data. It provides a terminologique ; dev/ simple API for diving into common natural PoS tagging ; language processing (NLP) tasks such as Analyse de part-of-speech tagging, noun phrase sentiments ; extraction, sentiment analysis, Classification ; classification, translation, and more. Traduction automatique ; Détection de la langue ; Tokenisation ; Parsing ; Correction orthographique ; TextCat http://odur.let.rug.nl/~vannoord/TextCat/ Libre Classification de Oui http://odur.let.rug.nl/~vannoord/ Pays-Bas ; textes ; TextCat/ TextObserver Outil de d’observation et d’exploitation Libre Textométrie ; Non http://textopol.u-pec.fr/textobserver/ France ; des données textuelles multidimensionnelles. TextRazor The TextRazor API helps you extract and Libre Reconnaissance Oui https://www.textrazor.com/ Royaume- understand the Who, What, Why and How d'entités nommées ; Uni from your news stories with Classification ; unprecedented accuracy and speed Annotation ; Désambiguisation ; Extraction de relations ; Extraction de mots clés ; Theano Deep learning Libre Apprentissage Non http://www.deeplearning.net/ Canada ; profond ; software/theano/

Thematic AI text analytics and visualizations Commercial Clustering ; Non https://getthematic.com/ ?

Mise à jour du 25 mars 2019 Inist - F. Arnould | 50 Outil Description Licence Tâche(s) OMTD Source Pays

Theysay Emotional AI and advanced data analytics Commercial Analyse de Non http://www.theysay.io/ Royaume- to stream, interpret, and bring together sentiments ; Uni ; opinions, moods, and feelings across the Analyse d'opinions ; Web. Think Analytics The ThinkAnalytics Search and Commercial Apprentissage Non https://thinkanalytics.com/ Royaume- Recommendations Engine provides a automatique ; Uni ; powerful, scalable, real-time and comprehensive multi-content/multi- platform Recommendations Engine supporting across content delivery of recommendations and search to multiple platforms such as the set top box, mobile, web, smart TV, games consoles, and others. Torch Torch is a scientific computing framework Libre Apprentissage Non http://torch.ch/ ? with wide support for machine learning automatique ; algorithms that puts GPUs first. It is easy to use and efficient, thanks to an easy and fast scripting language, LuaJIT, and an underlying C/CUDA implementation. TreeTagger The TreeTagger is a tool for annotating Libre PoS tagging ; Oui http://www.cis.uni-muenchen.de/ Allemagne ; text with part-of-speech and lemma Lemmatization ; ~schmid/tools/TreeTagger/ information Chunking ;

Tropes Analyse sémantique de textes Libre Textométrie ; Non http://www.tropes.fr/ France ;

Tweet NLP We provide a tokenizer, a part-of-speech Libre Tokenisation ; Oui ? http://www.cs.cmu.edu/~ark/ États-Unis ; tagger, hierarchical word clusters, and a PoS tagging ; TweetNLP/ dependency parser for tweets, along with Parsing ; annotated corpora and web-based Clustering ; annotation tools. Annotation ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 51 Outil Description Licence Tâche(s) OMTD Source Pays

TwinWord Text analysis APIS to understand and Commercial Analyse de Non https://www.twinword.com/ États-Unis ; associate words sentiments ; Clustering ; Classfication de textes ; Lemmatisation ; Extraction de mots clés ; TXM Analyses textométriques Libre Textométrie Non http://textometrie.ens-lyon.fr/ France ;

U-compare U-Compare is an integrated text mining/ Libre Annotation ; Non http://u-compare.org/ Japon ; natural language processing system Reconnaissance based on the UIMA Framework d'entités nommées ; Tokenisation ; PoS Tagging ; Lemmatisation ; Parsing ; Extraction d'évènements ; UAIC NLP The Natural Language Processing (NLP) Libre PoS tagging ; Oui http://nlptools.info.uaic.ro/ Roumanie Group at UAIC-FII has been involved in Chunking ; Resources.jsp many national and European projects Reconnaissance dealing with: morphology, information d'entités nommées ; retrieval, dialogue systems, anaphora Parsing; Sentence resolution, WordNet, discourse parsing splitting ; Résolution and summarization, question-answering, d'anaphore ; textual entailment, etc. UltiPro Understand what employees are saying Commercial Apprentissage Non https://www.ultimatesoftware.com/ États-Unis ; Perception and how they truly feel about the automatique ; UltiPro-Solution-Features- workplace, with surveys and sentiment Analyse d'opinions ; Employee-Surveys analysis. Unitex Open Source Corpus Processing Suite. Libre Reconnaissance Non http://unitexgramlab.org/ France ; d'entités nommées ; Désambiguïsation ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 52 Outil Description Licence Tâche(s) OMTD Source Pays

Vertica Data mining and analysis Commercial Apprentissage Non https://www.vertica.com/ États-Unis ; automatique ; VisualText Integrated development environment for Libre/ Extraction Non http://www.textanalysis.com/ États-Unis ; building information extraction systems, Commercial d'informations ; Products/products.html natural language processing systems, and Résumé text analyzers. automatique ; Clustering ; Reconnaissance d'entités nommées ; Recherche d'informations ; Annotation ; VizTrails Open-source scientific workflow and Libre Analyse de données Non https://www.vistrails.org/index.php/ États-Unis ; provenance management system that ; Main_Page supports data exploration and Visualisation ; visualization. VosViewer VOSviewer is a software tool for Libre Extraction Non http://www.vosviewer.com/ Pays-Bas ; constructing and visualizing bibliometric terminologique ; networks. These networks may for Co-occurrence ; instance include journals, researchers, or individual publications, and they can be constructed based on citation, bibliographic coupling, co-citation, or co- authorship relations. VOSviewer also offers text mining functionality that can be used to construct and visualize co- occurrence networks of important terms extracted from a body of scientific literature. Vowpal WAbbit The Vowpal Wabbit (VW) project is a fast Libre Classification ; Non https://github.com/JohnLangford/ États-Unis ; out-of-core learning system Analyse de vowpal_wabbit/wiki régression ;

Voyant Environnement en ligne de lecture et Libre Clustering ; Non http://voyant-tools.org/ Canada ; d’analyse de textes numériques. Concordancier ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 53 Outil Description Licence Tâche(s) OMTD Source Pays

Voziq Unify every customer experience data Commercial Analyse de Non http://voziq.com/ États-Unis ; source, and apply combined power of text sentiments ; analytics and predictive algorithms for Apprentissage strategic customer intelligence. automatique ; WarpLDA Cache efficient implementation for Latent Libre Topic modeling ; Non https://github.com/thu-ml/warplda Chine ; Dirichlet Allocation WebAnno WebAnno is a general purpose web- Libre Annotation Non https://webanno.github.io/webanno/ Allemagne ; based annotation tool for a wide range of sémantique ; linguistic annotations including various layers of morphological, syntactical, and semantic annotations.Additionaly, custom annotation layers can be defined, allowing WebAnno to be used also for non- linguistic annotation tasks. Weblicht WebLicht is an execution environment for Libre ? Tokenisation ; Oui https://weblicht.sfs.uni- Allemagne ; automatic annotation of text corpora. PoS tagging ; tuebingen.de/weblichtwiki/ Linguistic tools such as tokenizers, part of Parsing ; index.php/Main_Page speech taggers, and parsers are encapsulated as web services, which can be combined by the user into custom processing chains. The resulting annotations can then be visualized in an appropriate way, such as in a table or tree format. Weka Collection of machine learning algorithms Libre Classification ; Oui http://www.cs.waikato.ac.nz/ml/ Nouvelle- for data mining tasks. Clustering ; weka/ zélande ; Analyse de régression ; Arbre de décision ; Règle d'association ;

Mise à jour du 25 mars 2019 Inist - F. Arnould | 54 Outil Description Licence Tâche(s) OMTD Source Pays

Word2Vec Word embeddings Libre Apprentissage Non https://github.com/dav/word2vec États-Unis ; profond ; Plongement de mots WordFreak WordFreak is a java-based linguistic Libre Annotation ; Non http://wordfreak.sourceforge.net/ États-Unis ; annotation tool designed to support human, and automatic annotation of linguistic data as well as employ active- learning for human correction of automatically annotated data. YaTeA Term extraction Libre Extraction Oui http://search.cpan.org/~thhamon/ France ; terminologique ; Lingua-YaTeA-0.5/

Mise à jour du 25 mars 2019 Inist - F. Arnould | 55