Development of a Persian Syntactic Dependency Treebank
Total Page:16
File Type:pdf, Size:1020Kb
Load more
Recommended publications
-
How Do BERT Embeddings Organize Linguistic Knowledge?
How Do BERT Embeddings Organize Linguistic Knowledge? Giovanni Puccettiy , Alessio Miaschi? , Felice Dell’Orletta y Scuola Normale Superiore, Pisa ?Department of Computer Science, University of Pisa Istituto di Linguistica Computazionale “Antonio Zampolli”, Pisa ItaliaNLP Lab – www.italianlp.it [email protected], [email protected], [email protected] Abstract et al., 2019), we proposed an in-depth investigation Several studies investigated the linguistic in- aimed at understanding how the information en- formation implicitly encoded in Neural Lan- coded by BERT is arranged within its internal rep- guage Models. Most of these works focused resentation. In particular, we defined two research on quantifying the amount and type of in- questions, aimed at: (i) investigating the relation- formation available within their internal rep- ship between the sentence-level linguistic knowl- resentations and across their layers. In line edge encoded in a pre-trained version of BERT and with this scenario, we proposed a different the number of individual units involved in the en- study, based on Lasso regression, aimed at understanding how the information encoded coding of such knowledge; (ii) understanding how by BERT sentence-level representations is ar- these sentence-level properties are organized within ranged within its hidden units. Using a suite of the internal representations of BERT, identifying several probing tasks, we showed the existence groups of units more relevant for specific linguistic of a relationship between the implicit knowl- tasks. We defined a suite of probing tasks based on edge learned by the model and the number of a variable selection approach, in order to identify individual units involved in the encodings of which units in the internal representations of BERT this competence. -
Treebanks, Linguistic Theories and Applications Introduction to Treebanks
Treebanks, Linguistic Theories and Applications Introduction to Treebanks Lecture One Petya Osenova and Kiril Simov Sofia University “St. Kliment Ohridski”, Bulgaria Bulgarian Academy of Sciences, Bulgaria ESSLLI 2018 30th European Summer School in Logic, Language and Information (6 August – 17 August 2018) Plan of the Lecture • Definition of a treebank • The place of the treebank in the language modeling • Related terms: parsebank, dynamic treebank • Prerequisites for the creation of a treebank • Treebank lifecycle • Theory (in)dependency • Language (in)dependency • Tendences in the treebank development 30th European Summer School in Logic, Language and Information (6 August – 17 August 2018) Treebank Definition A corpus annotated with syntactic information • The information in the annotation is added/checked by a trained annotator - manual annotation • The annotation is complete - no unannotated fragments of the text • The annotation is consistent - similar fragments are analysed in the same way • The primary format of annotation - syntactic tree/graph 30th European Summer School in Logic, Language and Information (6 August – 17 August 2018) Example Syntactic Trees from Wikipedia The two main approaches to modeling the syntactic information 30th European Summer School in Logic, Language and Information (6 August – 17 August 2018) Pros vs. Cons (Handbook of NLP, p. 171) Constituency • Easy to read • Correspond to common grammatical knowledge (phrases) • Introduce arbitrary complexity Dependency • Flexible • Also correspond to common grammatical -
Senserelate::Allwords - a Broad Coverage Word Sense Tagger That Maximizes Semantic Relatedness
WordNet::SenseRelate::AllWords - A Broad Coverage Word Sense Tagger that Maximizes Semantic Relatedness Ted Pedersen and Varada Kolhatkar Department of Computer Science University of Minnesota Duluth, MN 55812 USA tpederse,kolha002 @d.umn.edu http://senserelate.sourceforge.net{ } Abstract Despite these difficulties, word sense disambigua- tion is often a necessary step in NLP and can’t sim- WordNet::SenseRelate::AllWords is a freely ply be ignored. The question arises as to how to de- available open source Perl package that as- velop broad coverage sense disambiguation modules signs a sense to every content word (known that can be deployed in a practical setting without in- to WordNet) in a text. It finds the sense of vesting huge sums in manual annotation efforts. Our each word that is most related to the senses answer is WordNet::SenseRelate::AllWords (SR- of surrounding words, based on measures found in WordNet::Similarity. This method is AW), a method that uses knowledge already avail- shown to be competitive with results from re- able in the lexical database WordNet to assign senses cent evaluations including SENSEVAL-2 and to every content word in text, and as such offers SENSEVAL-3. broad coverage and requires no manual annotation of training data. SR-AW finds the sense of each word that is most 1 Introduction related or most similar to those of its neighbors in the Word sense disambiguation is the task of assigning sentence, according to any of the ten measures avail- a sense to a word based on the context in which it able in WordNet::Similarity (Pedersen et al., 2004). -
Deep Linguistic Analysis for the Accurate Identification of Predicate
Deep Linguistic Analysis for the Accurate Identification of Predicate-Argument Relations Yusuke Miyao Jun'ichi Tsujii Department of Computer Science Department of Computer Science University of Tokyo University of Tokyo [email protected] CREST, JST [email protected] Abstract obtained by deep linguistic analysis (Gildea and This paper evaluates the accuracy of HPSG Hockenmaier, 2003; Chen and Rambow, 2003). parsing in terms of the identification of They employed a CCG (Steedman, 2000) or LTAG predicate-argument relations. We could directly (Schabes et al., 1988) parser to acquire syntac- compare the output of HPSG parsing with Prop- tic/semantic structures, which would be passed to Bank annotations, by assuming a unique map- statistical classifier as features. That is, they used ping from HPSG semantic representation into deep analysis as a preprocessor to obtain useful fea- PropBank annotation. Even though PropBank tures for training a probabilistic model or statistical was not used for the training of a disambigua- tion model, an HPSG parser achieved the ac- classifier of a semantic argument identifier. These curacy competitive with existing studies on the results imply the superiority of deep linguistic anal- task of identifying PropBank annotations. ysis for this task. Although the statistical approach seems a reason- 1 Introduction able way for developing an accurate identifier of Recently, deep linguistic analysis has successfully PropBank annotations, this study aims at establish- been applied to real-world texts. Several parsers ing a method of directly comparing the outputs of have been implemented in various grammar for- HPSG parsing with the PropBank annotation in or- malisms and empirical evaluation has been re- der to explicitly demonstrate the availability of deep ported: LFG (Riezler et al., 2002; Cahill et al., parsers. -
The Procedure of Lexico-Semantic Annotation of Składnica Treebank
The Procedure of Lexico-Semantic Annotation of Składnica Treebank Elzbieta˙ Hajnicz Institute of Computer Science, Polish Academy of Sciences ul. Ordona 21, 01-237 Warsaw, Poland [email protected] Abstract In this paper, the procedure of lexico-semantic annotation of Składnica Treebank using Polish WordNet is presented. Other semantically annotated corpora, in particular treebanks, are outlined first. Resources involved in annotation as well as a tool called Semantikon used for it are described. The main part of the paper is the analysis of the applied procedure. It consists of the basic and correction phases. During basic phase all nouns, verbs and adjectives are annotated with wordnet senses. The annotation is performed independently by two linguists. Multi-word units obtain special tags, synonyms and hypernyms are used for senses absent in Polish WordNet. Additionally, each sentence receives its general assessment. During the correction phase, conflicts are resolved by the linguist supervising the process. Finally, some statistics of the results of annotation are given, including inter-annotator agreement. The final resource is represented in XML files preserving the structure of Składnica. Keywords: treebanks, wordnets, semantic annotation, Polish 1. Introduction 2. Semantically Annotated Corpora It is widely acknowledged that linguistically annotated cor- Semantic annotation of text corpora seems to be the last pora play a crucial role in NLP. There is even a tendency phase in the process of corpus annotation, less popular than towards their ever-deeper annotation. In particular, seman- morphosyntactic and (shallow or deep) syntactic annota- tically annotated corpora become more and more popular tion. However, there exist semantically annotated subcor- as they have a number of applications in word sense disam- pora for many languages. -
Unified Language Model Pre-Training for Natural
Unified Language Model Pre-training for Natural Language Understanding and Generation Li Dong∗ Nan Yang∗ Wenhui Wang∗ Furu Wei∗† Xiaodong Liu Yu Wang Jianfeng Gao Ming Zhou Hsiao-Wuen Hon Microsoft Research {lidong1,nanya,wenwan,fuwei}@microsoft.com {xiaodl,yuwan,jfgao,mingzhou,hon}@microsoft.com Abstract This paper presents a new UNIfied pre-trained Language Model (UNILM) that can be fine-tuned for both natural language understanding and generation tasks. The model is pre-trained using three types of language modeling tasks: unidirec- tional, bidirectional, and sequence-to-sequence prediction. The unified modeling is achieved by employing a shared Transformer network and utilizing specific self-attention masks to control what context the prediction conditions on. UNILM compares favorably with BERT on the GLUE benchmark, and the SQuAD 2.0 and CoQA question answering tasks. Moreover, UNILM achieves new state-of- the-art results on five natural language generation datasets, including improving the CNN/DailyMail abstractive summarization ROUGE-L to 40.51 (2.04 absolute improvement), the Gigaword abstractive summarization ROUGE-L to 35.75 (0.86 absolute improvement), the CoQA generative question answering F1 score to 82.5 (37.1 absolute improvement), the SQuAD question generation BLEU-4 to 22.12 (3.75 absolute improvement), and the DSTC7 document-grounded dialog response generation NIST-4 to 2.67 (human performance is 2.65). The code and pre-trained models are available at https://github.com/microsoft/unilm. 1 Introduction Language model (LM) pre-training has substantially advanced the state of the art across a variety of natural language processing tasks [8, 29, 19, 31, 9, 1]. -
Spell Checker
International Journal of Scientific and Research Publications, Volume 5, Issue 4, April 2015 1 ISSN 2250-3153 SPELL CHECKER Vibhakti V. Bhaire, Ashiki A. Jadhav, Pradnya A. Pashte, Mr. Magdum P.G ComputerEngineering, Rajendra Mane College of Engineering and Technology Abstract- Spell Checker project adds spell checking and For handling morphology language-dependent algorithm is an correction functionality to the windows based application by additional step. The spell-checker will need to consider different using autosuggestion technique. It helps the user to reduce typing forms of the same word, such as verbal forms, contractions, work, by identifying any spelling errors and making it easier to possessives, and plurals, even for a lightly inflected language like repeat searches .The main goal of the spell checker is to provide English. For many other languages, such as those featuring unified treatment of various spell correction. Firstly the spell agglutination and more complex declension and conjugation, this checking and correcting problem will be formally describe in part of the process is more complicated. order to provide a better understanding of these task. Spell checker and corrector is either stand-alone application capable of A spell checker carries out the following processes: processing a string of words or a text or as an embedded tool which is part of a larger application such as a word processor. • It scans the text and selects the words contained in it. Various search and replace algorithms are adopted to fit into the • domain of spell checker. Spell checking identifies the words that It then compares each word with a known list of are valid in the language as well as misspelled words in the correctly spelled words (i.e. -
Building a Treebank for French
Building a treebank for French £ £¥ Anne Abeillé£ , Lionel Clément , Alexandra Kinyon ¥ £ TALaNa, Université Paris 7 University of Pennsylvania 75251 Paris cedex 05 Philadelphia FRANCE USA abeille, clement, [email protected] Abstract Very few gold standard annotated corpora are currently available for French. We present an ongoing project to build a reference treebank for French starting with a tagged newspaper corpus of 1 Million words (Abeillé et al., 1998), (Abeillé and Clément, 1999). Similarly to the Penn TreeBank (Marcus et al., 1993), we distinguish an automatic parsing phase followed by a second phase of systematic manual validation and correction. Similarly to the Prague treebank (Hajicova et al., 1998), we rely on several types of morphosyntactic and syntactic annotations for which we define extensive guidelines. Our goal is to provide a theory neutral, surface oriented, error free treebank for French. Similarly to the Negra project (Brants et al., 1999), we annotate both constituents and functional relations. 1. The tagged corpus pronoun (= him ) or a weak clitic pronoun (= to him or to As reported in (Abeillé and Clément, 1999), we present her), plus can either be a negative adverb (= not any more) the general methodology, the automatic tagging phase, the or a simple adverb (= more). Inflectional morphology also human validation phase and the final state of the tagged has to be annotated since morphological endings are impor- corpus. tant for gathering constituants (based on agreement marks) and also because lots of forms in French are ambiguous 1.1. Methodology with respect to mode, person, number or gender. For exam- 1.1.1. -
Converting an HPSG-Based Treebank Into Its Parallel Dependency-Based Treebank
Converting an HPSG-based Treebank into its Parallel Dependency-based Treebank Masood Ghayoomiy z Jonas Kuhnz yDepartment of Mathematics and Computer Science, Freie Universität Berlin z Institute for Natural Language Processing, University of Stuttgart [email protected] [email protected] Abstract A treebank is an important language resource for supervised statistical parsers. The parser induces the grammatical properties of a language from this language resource and uses the model to parse unseen data automatically. Since developing such a resource is very time-consuming and tedious, one can take advantage of already extant resources by adapting them to a particular application. This reduces the amount of human effort required to develop a new language resource. In this paper, we introduce an algorithm to convert an HPSG-based treebank into its parallel dependency-based treebank. With this converter, we can automatically create a new language resource from an existing treebank developed based on a grammar formalism. Our proposed algorithm is able to create both projective and non-projective dependency trees. Keywords: Treebank Conversion, the Persian Language, HPSG-based Treebank, Dependency-based Treebank 1. Introduction treebank is introduced in Section 4. The properties Supervised statistical parsers require a set of annotated of the available dependency treebanks for Persian and data, called a treebank, to learn the grammar of the their pros and cons are explained in Section 5. The target language and create a wide coverage grammar tools and the experimental setup as well as the ob- model to parse unseen data. Developing such a data tained results are described and discussed in Section source is a tedious and time-consuming task. -
Finite State Recognizer and String Similarity Based Spelling
View metadata, citation and similar papers at core.ac.uk brought to you by CORE provided by BRAC University Institutional Repository FINITE STATE RECOGNIZER AND STRING SIMILARITY BASED SPELLING CHECKER FOR BANGLA Submitted to A Thesis The Department of Computer Science and Engineering of BRAC University by Munshi Asadullah In Partial Fulfillment of the Requirements for the Degree of Bachelor of Science in Computer Science and Engineering Fall 2007 BRAC University, Dhaka, Bangladesh 1 DECLARATION I hereby declare that this thesis is based on the results found by me. Materials of work found by other researcher are mentioned by reference. This thesis, neither in whole nor in part, has been previously submitted for any degree. Signature of Supervisor Signature of Author 2 ACKNOWLEDGEMENTS Special thanks to my supervisor Mumit Khan without whom this work would have been very difficult. Thanks to Zahurul Islam for providing all the support that was required for this work. Also special thanks to the members of CRBLP at BRAC University, who has managed to take out some time from their busy schedule to support, help and give feedback on the implementation of this work. 3 Abstract A crucial figure of merit for a spelling checker is not just whether it can detect misspelled words, but also in how it ranks the suggestions for the word. Spelling checker algorithms using edit distance methods tend to produce a large number of possibilities for misspelled words. We propose an alternative approach to checking the spelling of Bangla text that uses a finite state automaton (FSA) to probabilistically create the suggestion list for a misspelled word. -
Spell Checking in Computer-Assisted Language Learning: a Study of Misspellings by Nonnative Writers of German
SPELL CHECKING IN COMPUTER-ASSISTED LANGUAGE LEARNING: A STUDY OF MISSPELLINGS BY NONNATIVE WRITERS OF GERMAN Anne Rimrott Diplom, Justus Liebig Universitat, 2002 THESIS SUBMITTED IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF MASTER OF ARTS In the Department of Linguistics O Anne Rimrott 2005 SIMON FRASER UNIVERSITY Spring 2005 All rights reserved. This work may not be reproduced in whole or in part, by photocopy or other means, without permission of the author. APPROVAL Name: Anne Rimrott Degree: Master of Arts Title of Thesis: Spell Checking in Computer-Assisted Language Learning: A Study of Misspellings by Nonnative Writers of German Examining Committee: Chair: Dr. Alexei Kochetov Assistant Professor, Department of Linguistics Dr. Trude Heift Senior Supervisor Associate Professor, Department of Linguistics Dr. Chung-hye Han Supervisor Assistant Professor, Department of Linguistics Dr. Maria Teresa Taboada Supervisor Assistant Professor, Department of Linguistics Dr. Mathias Schulze External Examiner Assistant Professor, Department of Germanic and Slavic Studies University of Waterloo Date DefendedIApproved: SIMON FRASER UNIVERSITY PARTIAL COPYRIGHT LICENCE The author, whose copyright is declared on the title page of this work, has granted to Simon Fraser University the right to lend this thesis, project or extended essay to users of the Simon Fraser University Library, and to make partial or single copies only for such users or in response to a request from the library of any other university, or other educational institution, on its own behalf or for one of its users. The author has further granted permission to Simon Fraser University to keep or make a digital copy for use in its circulating collection. -
Exploiting Wikipedia Semantics for Computing Word Associations
Exploiting Wikipedia Semantics for Computing Word Associations by Shahida Jabeen A thesis submitted to the Victoria University of Wellington in fulfilment of the requirements for the degree of Doctor of Philosophy in Computer Science. Victoria University of Wellington 2014 Abstract Semantic association computation is the process of automatically quan- tifying the strength of a semantic connection between two textual units based on various lexical and semantic relations such as hyponymy (car and vehicle) and functional associations (bank and manager). Humans have can infer implicit relationships between two textual units based on their knowledge about the world and their ability to reason about that knowledge. Automatically imitating this behavior is limited by restricted knowledge and poor ability to infer hidden relations. Various factors affect the performance of automated approaches to com- puting semantic association strength. One critical factor is the selection of a suitable knowledge source for extracting knowledge about the im- plicit semantic relations. In the past few years, semantic association com- putation approaches have started to exploit web-originated resources as substitutes for conventional lexical semantic resources such as thesauri, machine readable dictionaries and lexical databases. These conventional knowledge sources suffer from limitations such as coverage issues, high construction and maintenance costs and limited availability. To overcome these issues one solution is to use the wisdom of crowds in the form of collaboratively constructed knowledge sources. An excellent example of such knowledge sources is Wikipedia which stores detailed information not only about the concepts themselves but also about various aspects of the relations among concepts. The overall goal of this thesis is to demonstrate that using Wikipedia for computing word association strength yields better estimates of hu- mans’ associations than the approaches based on other structured and un- structured knowledge sources.