DOCSLIB.ORG

A Knowledge-Based Representation for Cross-Language Document Retrieval and Categorization

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
A Knowledge-Based Representation for Cross-Language Document Retrieval and Categorization A Knowledge-based Representation for Cross-Language Document Retrieval and Categorization Marc Franco-Salvador1;2, Paolo Rosso2 and Roberto Navigli1 1 Department of Computer Science Sapienza Universita` di Roma, Italy ffrancosalvador,[email protected] 2 Natural Language Engineering Lab - PRHLT Research Center Universitat Politecnica` de Valencia,` Spain fmfranco,[email protected] Abstract 1994), Latent Dirichlet Allocation (LDA) (Blei et al., 2003) and variants thereof, which project these Current approaches to cross-language doc- vectors into a lower-dimensional vector space. In ument retrieval and categorization are order to enable multilinguality, the vectors of com- based on discriminative methods which parable documents written in different languages represent documents in a low-dimensional are concatenated, making up the document ma- vector space. In this paper we pro- trix which is then reduced using linear projection pose a shift from the supervised to the (Platt et al., 2010; Yih et al., 2011). However, to knowledge-based paradigm and provide a do so, comparable documents are needed as train- document similarity measure which draws ing. Additionally, the lower dimensional represen- on BabelNet, a large multilingual knowl- tations are not of easy interpretation. edge resource. Our experiments show The availability of wide-coverage lexical state-of-the-art results in cross-lingual knowledge resources extracted automatically document retrieval and categorization. from Wikipedia, such as DBPedia (Bizer et al., 1 Introduction 2009), YAGO (Hoffart et al., 2013) and BabelNet (Navigli and Ponzetto, 2012a), has considerably The huge amount of text that is available on- boosted research in several areas, especially where line is becoming ever increasingly multilingual, multilinguality is a concern (Hovy et al., 2013). providing an additional wealth of useful informa- Among these latter are cross-language plagiarism tion. Most of this information, however, is not eas- detection (Potthast et al., 2011; Franco-Salvador ily accessible to the majority of users because of et al., 2013), multilingual semantic relatedness language barriers which hamper the cross-lingual (Navigli and Ponzetto, 2012b; Nastase and search and retrieval of knowledge. Strube, 2013) and semantic alignment (Navigli Today’s search engines would benefit greatly and Ponzetto, 2012a; Matuschek and Gurevych, from effective techniques for the cross-lingual re- 2013). One main advantage of knowledge-based trieval of valuable information that can satisfy methods is that they provide a human-readable, a user’s needs by not only providing (Landauer semantically interconnected, representation of and Littman, 1994) and translating (Munteanu and the textual item at hand (be it a sentence or a Marcu, 2005) relevant results into different lan- document). guages, but also by reranking the results in a lan- Following this trend, in this paper we provide guage of interest on the basis of the importance of a knowledge-based representation of documents search results in other languages. which goes beyond the lexical surface of text, Vector-based models are typically used in the while at the same time avoiding the need for train- literature for representing documents both in ing in a cross-language setting. To achieve this monolingual and cross-lingual settings (Manning we leverage a multilingual semantic network, i.e., et al., 2008). However, because of the large size BabelNet, to obtain language-independent repre- of the vocabulary, having each term as a compo- sentations, which contain concepts together with nent of the vector makes the document represen- semantic relations between them, and also include tation very sparse. To address this issue several semantic knowledge which is just implied by the approaches to dimensionality reduction have been input text. The integration of our multilingual proposed, such as Principal Component Analysis graph model with a vector representation enables (Jolliffe, 1986), Latent Semantic Indexing (Hull, us to obtain state-of-the-art results in comparable document retrieval and cross-language text cate- 2010; Yih et al., 2011). Cross-language Latent Se- gorization. mantic Indexing (CL-LSI) (Dumais et al., 1997) was the first linear projection approach used in 2 Related Work cross-lingual tasks. CL-LSI provides a cross- lingual representation for documents by reducing The mainstream representation of documents the dimensionality of a matrix D whose rows are for monolingual and cross-lingual document re- obtained by concatenating comparable documents trieval is vector-based. A document vector, whose from different languages. Similarly, PCA and components quantify the relevance of each term in OPCA can be adapted to a multilingual setting. the document, is usually highly dimensional, be- LDA was also adapted to perform in a multilingual cause of the variety of terms used in a document scenario with models such as Polylingual Topic collection. As a consequence, the resulting docu- Models (Mimno et al., 2009), Joint Probabilistic ment matrices are very sparse. To address the data LSA and Coupled Probabilistic LSA (Platt et al., sparsity issue, several approaches to the reduc- 2010), which, however, are constrained to using tion of dimensionality of document vectors have word counts, instead of better weighting strate- been proposed in the literature. A popular class of gies, such as log(tf)-idf, known to perform bet- methods is based on linear projection, which pro- ter with large vocabularies (Salton and McGill, vides a low-dimensional mapping from a high di- 1986). Another variant, named Canonical Cor- mensional vector space. A historical approach to relation Analysis (CCA) (Thompson, 2005), uses linear projection is Principal Component Analysis a cross-covariance matrix of the low-dimensional (PCA) (Jolliffe, 1986), which performs a singular vectors to find the projections. Cross-language value decomposition (SVD) on a document matrix Explicit Semantic Analysis (CL-ESA) (Potthast et D of size n × m, where each row in D is the term al., 2008; Cimiano et al., 2009; Potthast et al., vector representation of a document. PCA uses 2011), instead, adapts ESA to be used at cross- an orthogonal transformation to convert a set of language level by exploiting the comparable docu- observations of possibly correlated variables into ments across languages from Wikipedia. CL-ESA a set of values of linearly uncorrelated variables represents each document written in a language called principal components, which make up the L by its similarities with a document collection low-dimensional vector. Latent Semantic Analy- in language L. Using a multilingual document sis (LSA) (Deerwester et al., 1990) is very simi- collection with comparable documents across lan- lar to PCA but performs the SVD using the cor- guages, the resulting vectors from different lan- relation matrix instead of the covariance matrix, guages can be compared directly. which implies a lower computational cost. LSA An alternative unsupervised approach, Cross- preserves the amount of variance in an eigenvector language Character n-Grams (CL-CNG) (Mc- ~vT C~v ~v by maximizing its Rayleigh ratio: ~vT ~v , where namee and Mayfield, 2004), does not draw upon C = DT D is the correlation matrix of D. linear projections and represents documents as A generalization of PCA, called Oriented Prin- vectors of character n-grams. It has proven to ob- cipal Component Analysis (OPCA) (Diamantaras tain good results in cross-language document re- and Kung, 1996), is based on a noise covari- trieval (Potthast et al., 2011) between languages ance matrix to project the similar components of with lexical and syntactic similarities. D closely. Other projection models such as La- Recently, a novel supervised linear projec- tent Dirichlet Allocation (LDA) (Blei et al., 2003) tion model based on Siamese Neural Networks are based on the extraction of generative models (S2Net) (Yih et al., 2011) achieved state-of-the- from documents. Another approach, named Ex- art performance in comparable document retrieval. plicit Semantic Analysis (ESA) (Gabrilovich and S2Net performs a linear combination of the terms Markovitch, 2007), represents each document by of a document vector d~ to obtain a reduced vector its similarities to a document collection. Using a ~r, which is the output layer of a neural network. low domain specificity document collection such Each element in ~r has a weight which is a linear as Wikipedia, the model has proven to obtain com- combination of the original weights of d~, and cap- petitive results. tures relationships between the original terms. Not only have these methods proven to be suc- However, linear projection approaches need a cessful in a monolingual scenario (Deerwester high number of training documents to achieve et al., 1990; Hull, 1994), but they have also state-of-the-art performance (Platt et al., 2010; been adapted to perform well in tasks at a cross- Yih et al., 2011). Moreover, although they are language level (Potthast et al., 2008; Platt et al., good at identifying a few principal components, the representations produced are opaque, in that icographic and encyclopedic knowledge, and its they cannot explicitly model the semantic content free availability.1 In our work we used BabelNet of documents with a human-interpretable repre- 1.0, which encodes knowledge for six languages, sentation, thereby making the data analysis diffi- namely: Catalan, English, French, German, Italian cult.
Load more

Recommended publications
  • Knowledge Graphs on the Web – an Overview Arxiv:2003.00719V3 [Cs
    January 2020 Knowledge Graphs on the Web – an Overview Nicolas HEIST, Sven HERTLING, Daniel RINGLER, and Heiko PAULHEIM Data and Web Science Group, University of Mannheim, Germany Abstract. Knowledge Graphs are an emerging form of knowledge representation. While Google coined the term Knowledge Graph first and promoted it as a means to improve their search results, they are used in many applications today. In a knowl- edge graph, entities in the real world and/or a business domain (e.g., people, places, or events) are represented as nodes, which are connected by edges representing the relations between those entities. While companies such as Google, Microsoft, and Facebook have their own, non-public knowledge graphs, there is also a larger body of publicly available knowledge graphs, such as DBpedia or Wikidata. In this chap- ter, we provide an overview and comparison of those publicly available knowledge graphs, and give insights into their contents, size, coverage, and overlap. Keywords. Knowledge Graph, Linked Data, Semantic Web, Profiling 1. Introduction Knowledge Graphs are increasingly used as means to represent knowledge. Due to their versatile means of representation, they can be used to integrate different heterogeneous data sources, both within as well as across organizations. [8,9] Besides such domain-specific knowledge graphs which are typically developed for specific domains and/or use cases, there are also public, cross-domain knowledge graphs encoding common knowledge, such as DBpedia, Wikidata, or YAGO. [33] Such knowl- edge graphs may be used, e.g., for automatically enriching data with background knowl- arXiv:2003.00719v3 [cs.AI] 12 Mar 2020 edge to be used in knowledge-intensive downstream applications.
    [Show full text]
  • Detecting Personal Life Events from Social Media
    Open Research Online The Open University’s repository of research publications and other research outputs Detecting Personal Life Events from Social Media Thesis How to cite: Dickinson, Thomas Kier (2019). Detecting Personal Life Events from Social Media. PhD thesis The Open University. For guidance on citations see FAQs. c 2018 The Author https://creativecommons.org/licenses/by-nc-nd/4.0/ Version: Version of Record Link(s) to article on publisher’s website: http://dx.doi.org/doi:10.21954/ou.ro.00010aa9 Copyright and Moral Rights for the articles on this site are retained by the individual authors and/or other copyright owners. For more information on Open Research Online’s data policy on reuse of materials please consult the policies page. oro.open.ac.uk Detecting Personal Life Events from Social Media a thesis presented by Thomas K. Dickinson to The Department of Science, Technology, Engineering and Mathematics in partial fulfilment of the requirements for the degree of Doctor of Philosophy in the subject of Computer Science The Open University Milton Keynes, England May 2019 Thesis advisor: Professor Harith Alani & Dr Paul Mulholland Thomas K. Dickinson Detecting Personal Life Events from Social Media Abstract Social media has become a dominating force over the past 15 years, with the rise of sites such as Facebook, Instagram, and Twitter. Some of us have been with these sites since the start, posting all about our personal lives and building up a digital identify of ourselves. But within this myriad of posts, what actually matters to us, and what do our digital identities tell people about ourselves? One way that we can start to filter through this data, is to build classifiers that can identify posts about our personal life events, allowing us to start to self reflect on what we share online.
    [Show full text]
  • Unsupervised, Knowledge-Free, and Interpretable Word Sense Disambiguation
    Unsupervised, Knowledge-Free, and Interpretable Word Sense Disambiguation Alexander Panchenkoz, Fide Martenz, Eugen Ruppertz, Stefano Faralliy, Dmitry Ustalov∗, Simone Paolo Ponzettoy, and Chris Biemannz zLanguage Technology Group, Department of Informatics, Universitat¨ Hamburg, Germany yWeb and Data Science Group, Department of Informatics, Universitat¨ Mannheim, Germany ∗Institute of Natural Sciences and Mathematics, Ural Federal University, Russia fpanchenko,marten,ruppert,[email protected] fsimone,[email protected] [email protected] Abstract manually in one of the underlying resources, such as Wikipedia. Unsupervised knowledge-free ap- Interpretability of a predictive model is proaches, e.g. (Di Marco and Navigli, 2013; Bar- a powerful feature that gains the trust of tunov et al., 2016), require no manual labor, but users in the correctness of the predictions. the resulting sense representations lack the above- In word sense disambiguation (WSD), mentioned features enabling interpretability. For knowledge-based systems tend to be much instance, systems based on sense embeddings are more interpretable than knowledge-free based on dense uninterpretable vectors. Therefore, counterparts as they rely on the wealth of the meaning of a sense can be interpreted only on manually-encoded elements representing the basis of a list of related senses. word senses, such as hypernyms, usage We present a system that brings interpretability examples, and images. We present a WSD of the knowledge-based sense representations into system that bridges the gap between these the world of unsupervised knowledge-free WSD two so far disconnected groups of meth- models. The contribution of this paper is the first ods. Namely, our system, providing access system for word sense induction and disambigua- to several state-of-the-art WSD models, tion, which is unsupervised, knowledge-free, and aims to be interpretable as a knowledge- interpretable at the same time.
    [Show full text]
  • Ten Years of Babelnet: a Survey
    Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI-21) Survey Track Ten Years of BabelNet: A Survey Roberto Navigli1 , Michele Bevilacqua1 , Simone Conia1 , Dario Montagnini2 and Francesco Cecconi2 1Sapienza NLP Group, Sapienza University of Rome, Italy 2Babelscape, Italy froberto.navigli, michele.bevilacqua, [email protected] fmontagnini, [email protected] Abstract to integrate symbolic knowledge into neural architectures [d’Avila Garcez and Lamb, 2020]. The rationale is that the The intelligent manipulation of symbolic knowl- use of, and linkage to, symbolic knowledge can not only en- edge has been a long-sought goal of AI. How- able interpretable, explainable and accountable AI systems, ever, when it comes to Natural Language Process- but it can also increase the degree of generalization to rare ing (NLP), symbols have to be mapped to words patterns (e.g., infrequent meanings) and promote better use and phrases, which are not only ambiguous but also of information which is not explicit in the text. language-specific: multilinguality is indeed a de- Symbolic knowledge requires that the link between form sirable property for NLP systems, and one which and meaning be made explicit, connecting strings to repre- enables the generalization of tasks where multiple sentations of concepts, entities and thoughts. Historical re- languages need to be dealt with, without translat- sources such as WordNet [Miller, 1995] are important en- ing text. In this paper we survey BabelNet, a pop- deavors which systematize symbolic knowledge about the ular wide-coverage lexical-semantic knowledge re- words of a language, i.e., lexicographic knowledge, not only source obtained by merging heterogeneous sources in a machine-readable format, but also in structured form, into a unified semantic network that helps to scale thanks to the organization of concepts into a semantic net- tasks and applications to hundreds of languages.
    [Show full text]
  • KOI at Semeval-2018 Task 5: Building Knowledge Graph of Incidents
    KOI at SemEval-2018 Task 5: Building Knowledge Graph of Incidents 1 2 2 Paramita Mirza, Fariz Darari, ∗ Rahmad Mahendra ∗ 1 Max Planck Institute for Informatics, Germany 2 Faculty of Computer Science, Universitas Indonesia, Indonesia paramita @mpi-inf.mpg.de fariz,rahmad.mahendra{ } @cs.ui.ac.id { } Abstract Subtask S3 In order to answer questions of type (ii), participating systems are also required We present KOI (Knowledge of Incidents), a to identify participant roles in each identified an- system that given news articles as input, builds swer incident (e.g., victim, subject-suspect), and a knowledge graph (KOI-KG) of incidental use such information along with victim-related nu- events. KOI-KG can then be used to effi- merals (“three people were killed”) mentioned in ciently answer questions such as “How many the corresponding answer documents, i.e., docu- killing incidents happened in 2017 that involve ments that report on the answer incident, to deter- Sean?” The required steps in building the KG include: (i) document preprocessing involv- mine the total number of victims. ing word sense disambiguation, named-entity Datasets The organizers released two datasets: recognition, temporal expression recognition and normalization, and semantic role labeling; (i) test data, stemming from three domains of (ii) incidental event extraction and coreference gun violence, fire disasters and business, and (ii) resolution via document clustering; and (iii) trial data, covering only the gun violence domain. KG construction and population. Each dataset
    [Show full text]
  • Web Search Result Clustering with Babelnet
    Web Search Result Clustering with BabelNet Marek Kozlowski Maciej Kazula OPI-PIB OPI-PIB [email protected] [email protected] Abstract 2 Related Work In this paper we present well-known 2.1 Search Result Clustering search result clustering method enriched with BabelNet information. The goal is The goal of text clustering in information retrieval to verify how Babelnet/Babelfy can im- is to discover groups of semantically related docu- prove the clustering quality in the web ments. Contextual descriptions (snippets) of docu- search results domain. During the evalua- ments returned by a search engine are short, often tion we tested three algorithms (Bisecting incomplete, and highly biased toward the query, so K-Means, STC, Lingo). At the first stage, establishing a notion of proximity between docu- we performed experiments only with tex- ments is a challenging task that is called Search tual features coming from snippets. Next, Result Clustering (SRC). Search Results Cluster- we introduced new semantic features from ing (SRC) is a specific area of documents cluster- BabelNet (as disambiguated synsets, cate- ing. gories and glosses describing synsets, or Approaches to search result clustering can be semantic edges) in order to verify how classified as data-centric or description-centric they influence on the clustering quality (Carpineto, 2009). of the search result clustering. The al- The data-centric approach (as Bisecting K- gorithms were evaluated on AMBIENT Means) focuses more on the problem of data clus- dataset in terms of the clustering quality. tering, rather than presenting the results to the user. Other data-centric methods use hierarchical 1 Introduction agglomerative clustering (Maarek, 2000) that re- In the previous years, Web clustering engines places single terms with lexical affinities (2-grams (Carpineto, 2009) have been proposed as a solu- of words) as features, or exploit link information tion to the issue of lexical ambiguity in Informa- (Zhang, 2008).
    [Show full text]
  • Oasics-ICLP-2017-13.Pdf (0.4
    Achieving High Quality Knowledge Acquisition using Controlled Natural Language Tiantian Gao∗ Department of Computer Science, Stony Brook University, Stony Brook, NY, USA [email protected] Abstract Controlled Natural Languages (CNLs) are efficient languages for knowledge acquisition and reas- oning. They are designed as a subset of natural languages with restricted grammar while being highly expressive. CNLs are designed to be automatically translated into logical representations, which can be fed into rule engines for query and reasoning. In this work, we build a knowledge acquisition machine, called KAM, that extends Attempto Controlled English (ACE) and achieves three goals. First, KAM can identify CNL sentences that correspond to the same logical rep- resentation but expressed in various syntactical forms. Second, KAM provides a graphical user interface (GUI) that allows users to disambiguate the knowledge acquired from text and incorpor- ates user feedback to improve knowledge acquisition quality. Third, KAM uses a paraconsistent logical framework to encode CNL sentences in order to achieve reasoning in the presence of inconsistent knowledge. 1998 ACM Subject Classification I.2.1 Applications and Expert Systems Keywords and phrases Logic Programming, Controlled Natural Languages, Knowledge Acquis- ition Digital Object Identifier 10.4230/OASIcs.ICLP.2017.13 1 Introduction Much of human knowledge can be represented as rules and facts, which can be used by rule engines (e.g., XSB [22], Clingo [9], IDP [5]) to conduct formal logical reasoning in order to derive new conclusions, answer questions, or explain the validity of true statements. However, rules and facts extracted from human knowledge can be very complex in the real world.
    [Show full text]
  • From Strings to Things SAR-Graphs: a New Type of Resource for Connecting Knowledge and Language
    From Strings to Things SAR-Graphs: A New Type of Resource for Connecting Knowledge and Language Hans Uszkoreit and Feiyu Xu Language Technology Lab, DFKI, Alt-Moabit 91c, Berlin, Germany {uszkoreit,feiyu}@dfki.de Abstract. Recent research and development have created the necessary ingredients for a major push in web-scale language understanding: large repositories of structured knowledge (DBpedia, the Google knowledge graph, Freebase, YAGO) progress in language processing (parsing, infor- mation extraction, computational semantics), linguistic knowledge re- sources (Treebanks, WordNet, BabelNet, UWN) and new powerful tech- niques for machine learning. A major goal is the automatic aggregation of knowledge from textual data. A central component of this endeavor is relation extraction (RE). In this paper, we will outline a new approach to connecting repositories of world knowledge with linguistic knowledge (syntactic and lexical semantics) via web-scale relation extraction tech- nologies. Keywords: Knowledge Graph, Grammar-based Relation Extraction Rules, Relation- specific lexical semantic graphs, Linking linguistic resources 1 Motivation The powerful vision of a semantic web has already started materializing through large repositories of structured knowledge extracted from Wikipedia and other sources of texts or data bases. The existence of these knowledge resources and further progress in linking open data collections has nurtured the demand for even more extensive sources of structured knowledge. Although some (linked) open data collections can feed into the stock of digital knowledge, the most effec- tive growth is expected from automatic extraction of information and knowledge out of texts. Knowledge repositories such as the DBpedia [1] are not only driv- ing advanced research in this important field but they also serve as important resources for the applied learning methods.
    [Show full text]
  • The Interplay Between Lexical Resources and Natural Language Processing
    Tutorial on: The interplay between lexical resources and Natural Language Processing Google Group: goo.gl/JEazYH 1 Luis Espinosa Anke Jose Camacho-Collados Mohammad Taher Pilehvar Google Group: goo.gl/JEazYH 2 Luis Espinosa Anke (linguist) Jose Camacho-Collados (mathematician) Mohammad Taher Pilehvar (computer scientist) 3 www.kahoot.it PIN: 7024700 NAACL 2018 Tutorial: The Interplay between Lexical Resources and Natural Language Processing Camacho-Collados, Espinosa-Anke, Pilehvar 4 QUESTION 1 PIN: 7024700 www.kahoot.it NAACL 2018 Tutorial: The Interplay between Lexical Resources and Natural Language Processing Camacho-Collados, Espinosa-Anke, Pilehvar 5 Outline 1. Introduction 2. Overview of Lexical Resources 3. NLP for Lexical Resources 4. Lexical Resources for NLP 5. Conclusion and Future Directions NAACL 2018 Tutorial: The Interplay between Lexical Resources and Natural Language Processing Camacho-Collados, Espinosa-Anke, Pilehvar 6 INTRODUCTION NAACL 2018 Tutorial: The Interplay between Lexical Resources and Natural Language Processing Camacho-Collados, Espinosa-Anke, Pilehvar 7 Introduction ● “A lexical resource (LR) is a database consisting of one or several dictionaries.” (en.wikipedia.org/wiki/Lexical_resource) ● “What is lexical resource? In a word it is vocabulary and it matters for IELTS writing because …” (dcielts.com/ielts-writing/lexical-resource) ● “The term Language Resource refers to a set of speech or language data and descriptions in machine readable form, used for … ” (elra.info/en/about/what-language-resource )
    [Show full text]
  • Semantic-Based Multilingual Document Clustering Via Tensor Modeling
    Semantic-Based Multilingual Document Clustering via Tensor Modeling Salvatore Romeo, Andrea Tagarelli Dino Ienco DIMES, University of Calabria IRSTEA, UMR TETIS Arcavacata di Rende, Italy Montpellier, France [email protected] LIRMM [email protected] Montpellier, France [email protected] Abstract through machine translation techniques based on a se- lected anchor language. Conversely, a comparable cor- A major challenge in document clustering re- pus is a collection of multilingual documents written search arises from the growing amount of text over the same set of classes (Ni et al., 2011; Yo- data written in different languages. Previ- gatama and Tanaka-Ishii, 2009) without any restric- ous approaches depend on language-specific tion about translation or perfect correspondence be- solutions (e.g., bilingual dictionaries, sequen- tween documents. To mine this kind of corpus, external tial machine translation) to evaluate document knowledge is employed to map concepts or terms from similarities, and the required transformations a language to another (Kumar et al., 2011c; Kumar may alter the original document semantics. To et al., 2011a), which enables the extraction of cross- cope with this issue we propose a new docu- lingual document correlations. In this case, a major ment clustering approach for multilingual cor- issue lies in the definition of a cross-lingual similarity pora that (i) exploits a large-scale multilingual measure that can fit the extracted cross-lingual correla- knowledge base, (ii) takes advantage of the tions. Also, from a semi-supervised perspective, other multi-topic nature of the text documents, and works attempt to define must-link constraints to de- (iii) employs a tensor-based model to deal with tect cross-lingual clusters (Yogatama and Tanaka-Ishii, high dimensionality and sparseness.
    [Show full text]
  • Dbpedia Based Factual Questions Answering System
    IADIS International Journal on WWW/Internet Vol. 15, No. 1, pp. 80-95 ISSN: 1645-7641 DBPEDIA BASED FACTUAL QUESTIONS ANSWERING SYSTEM Maksym Ketsmur1, Mário Rodrigues2 and António Teixeira1 1Department of Electronics Telecommunications and Informatics / IEETA, University of Aveiro. Portugal 2Águeda School of Technology and Management / IEETA, University of Aveiro. Portugal ABSTRACT The creation of generic natural language query and answering (QA) systems is an active goal of the Semantic Web since it would allow people to conduct any query using their native language. Current solutions already handle factual questions mostly in English. The aim of this work was to develop a QA system to query knowledge bases (KB) such as DBpedia, in a first version, using factual questions in Portuguese, and in a second version, factual questions in English, French and German. This involves representing queries in terms of the KB ontology using SPARQL. The process of constructing a SPARQL query representing the natural language input involves determining: (1) the type of answer that is being sought - a person, a place, etc. - which is done by looking at the wh-words of wh-questions; (2) the main topic of the question - which person, place, etc. - obtained by morphosyntactic analysis to discover the potential subjects of the question; and (3) the properties that can be mapped to the KB ontology for creating a SPARQL query as precise as possible. The first version of the system, working for Portuguese, was tested by with 22 questions without guarantee that the answer was in the KB, and the multilingual version was tested with 30 random questions from QALD 7 (Question Answering over Linked Data) training set.
    [Show full text]
  • Talking Open Data
    Talking Open Data Sebastian Neumaier, Vadim Savenkov, and Svitlana Vakulenko Vienna University of Economics and Business Institute for Information Business [email protected] Abstract. Enticing users into exploring Open Data remains an impor- tant challenge for the whole Open Data paradigm. Standard stock inter- faces often used by Open Data portals are anything but inspiring even for tech-savvy users, let alone those without an articulated interest in data science. To address a broader range of citizens, we designed an open data search interface supporting natural language interactions via popu- lar platforms like Facebook and Skype. Our data-aware chatbot answers search requests and suggests relevant open datasets, bringing fun factor and a potential of viral dissemination into Open Data exploration. The current system prototype is available for Facebook1 and Skype2 users. 1 Introduction The European Commission defines Open Data portals as \web-based interfaces designed to make it easier to find re-usable information"3. It is exactly the task of finding re-usable information, however, where current data portals fall short: they focus on supporting users to find files and not the information. It remains a tedious task for users to drill out and understand the information behind the data. According to the EU Data Portal study, 73% of the open data users characterize finding data as Difficult or Very Difficult 4. Currently, the data is brought to end users not directly but through apps, each focusing on a specific service and based on a handful of open datasets. The app ecosystem, promoted by Open Data portals, is thriving.
    [Show full text]