Filters








6,155 Hits in 3.3 sec

New experiments in distributional representations of synonymy

Dayne Freitag, Matthias Blume, John Byrnes, Edmond Chow, Sadik Kapadia, Richard Rohwer, Zhiqiang Wang
2005 Proceedings of the Ninth Conference on Computational Natural Language Learning - CONLL '05   unpublished
Recent work on the problem of detecting synonymy through corpus analysis has used the Test of English as a Foreign Language (TOEFL) as a benchmark.  ...  We overcome this limitation by generating a TOEFL-like test using WordNet, containing thousands of questions and composed only of words occurring with sufficient corpus frequency to support sound distributional  ...  Any opinions, findings, conclusions, or recommendations expressed in this material are those of the authors, and do not necessarily reflect the views of the U.S. Government.  ... 
doi:10.3115/1706543.1706548 fatcat:ykkngyhlnnaqtdszfqzyj3kpdu

Term representation with Generalized Latent Semantic Analysis [chapter]

Irina Matveeva, Gina-Anne Levow, Ayman Farahat, Christiaan Royer
2007 Current issues in linguistic theory  
Our experiments demonstrate that GLSA term vectors efficiently capture semantic relations between terms and outperform related approaches on the synonymy test.  ...  Document indexing and representation of termdocument relations are very important issues for document clustering and retrieval.  ...  Landauer, Department of Psychology, University of Colorado. This research has been funded in part by contract #MDA904-03-C-0404 to Stuart K.  ... 
doi:10.1075/cilt.292.08mat fatcat:feynf6rvdjau3b34sojl7xpxd4

Concurrent Learning of Semantic Relations [article]

Georgios Balikas, Gaël Dias, Rumen Moraliyski, Massih-Reza Amini
2018 arXiv   pre-print
Preliminary results based on simple learning strategies and state-of-the-art distributional feature representations show that concurrent learning can lead to improvements in a vast majority of tested situations  ...  multiple semantic relations (e.g. hypernymy vs. synonymy vs. random).  ...  In distributional methods, the decision whether x is within a semantic relation with y is based on the distributional representation of these words following the distributional hypothesis (Harris, 1954  ... 
arXiv:1807.10076v3 fatcat:hrqp3bkl45curfmxacuj3yuwra

Unraveling Antonym's Word Vectors through a Siamese-like Network

Mathias Etcheverry, Dina Wonsever
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
The approach makes use of the claim that the antonyms in common of a word tend to be synonyms.  ...  Consequently, pairs of antonyms and synonyms may have similar word vectors. We present an approach to unravel antonymy and synonymy from word vectors based on a siamese network inspired approach.  ...  Many research studies and experiments have focused on the construction of vector representations that deem antonymy.  ... 
doi:10.18653/v1/p19-1319 dblp:conf/acl/EtcheverryW19 fatcat:gogkuex7qfbyvdj6ya4asthmfe

Exploring the Representation of Word Meanings in Context: A Case Study on Homonymy and Synonymy [article]

Marcos Garcia
2021 arXiv   pre-print
This paper presents a multilingual study of word meaning representations in context.  ...  Experiments are performed in Galician, Portuguese, English, and Spanish, and both the dataset (with more than 3,000 evaluation items) and new models are freely released with this study.  ...  Acknowledgments We would like to thank the anonymous reviewers for their valuable comments, and NVIDIA Corporation for the donation of a Titan Xp GPU.  ... 
arXiv:2106.13553v2 fatcat:fcuvoh6i7fcl3fhlpxyv2m2wny

Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints [article]

Nikola Mrkšić, Ivan Vulić, Diarmuid Ó Séaghdha, Ira Leviant, Roi Reichart, Milica Gašić, Anna Korhonen, Steve Young
2017 arXiv   pre-print
The effectiveness of our approach is demonstrated with state-of-the-art results on semantic similarity datasets in six languages.  ...  We next show that Attract-Repel-specialised vectors boost performance in the downstream task of dialogue state tracking (DST) across multiple languages.  ...  In our experiments, the remaining six languages (HE, HR, SV, GA, VI, FA) serve as examples of lower-resource languages, as they have no monolingual synonymy constraints.  ... 
arXiv:1706.00374v1 fatcat:6ol3mrpjjrgb3bmzcwlzsz4oru

Counter-fitting Word Vectors to Linguistic Constraints [article]

Nikola Mrkšić and Diarmuid Ó Séaghdha and Blaise Thomson and Milica Gašić and Lina Rojas-Barahona and Pei-Hao Su and David Vandyke and Tsung-Hsien Wen and Steve Young
2016 arXiv   pre-print
In this work, we present a novel counter-fitting method which injects antonymy and synonymy constraints into vector space representations in order to improve the vectors' capability for judging semantic  ...  Applying this method to publicly available pre-trained word vectors leads to a new state of the art performance on the SimLex-999 dataset.  ...  A new feature of this version is that it assigns relation types to its word pairs. We identify the Equivalence relation with synonymy and Exclusion with antonymy.  ... 
arXiv:1603.00892v1 fatcat:rhylbl3sfre7tgslno4b7msd2m

Counter-fitting Word Vectors to Linguistic Constraints

Nikola Mrkšić, Diarmuid Ó Séaghdha, Blaise Thomson, Milica Gašić, Lina M. Rojas-Barahona, Pei-Hao Su, David Vandyke, Tsung-Hsien Wen, Steve Young
2016 Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies  
In this work, we present a novel counter-fitting method which injects antonymy and synonymy constraints into vector space representations in order to improve the vectors' capability for judging semantic  ...  Applying this method to publicly available pre-trained word vectors leads to a new state of the art performance on the SimLex-999 dataset.  ...  A new feature of this version is that it assigns relation types to its word pairs. We identify the Equivalence relation with synonymy and Exclusion with antonymy.  ... 
doi:10.18653/v1/n16-1018 dblp:conf/naacl/MrksicSTGRSVWY16 fatcat:tkgvcyo7m5ggjh2tcacjzbrbuq

Bag of Visual Words Method based on PLSA and Chi-Square Model for Object Category

2015 KSII Transactions on Internet and Information Systems  
The problem of visual words' synonymy and ambiguity always exist in the conventional bag of visual words (BoVW) model based object category methods.  ...  Firstly, Probabilistic Latent Semantic Analysis (PLSA) is used to analyze the semantic co-occurrence probability of visual words, infer the latent semantic topics in images, and get the latent topic distributions  ...  However, there exists some synonymy and ambiguity problems in visual words [13] [14] [15] as well as the seriously quantization error of compact histogram representation.  ... 
doi:10.3837/tiis.2015.07.017 fatcat:zivtlh3qvnaxrktymp4743or6e

Lexical semantic relatedness and online new event detection (poster session)

Nicola Stokes, Paula Hatch, Joe Carthy
2000 Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '00  
Summary In this paper we propose a novel use for lexical chains as document representations within the Topic Detection domain. Acknowledgments  ...  Description of Experiment Our new approach to document representation is based on the idea of conceptual indexing using lexical chaining.  ...  In particular, we are concerned with the huge increase in the availability of multiple news sources reporting essentially the same news.  ... 
doi:10.1145/345508.345623 dblp:conf/sigir/StokesHC00 fatcat:xffijz3ysvfynjobtuanlsuq7m

Using the Outlier Detection Task to Evaluate Distributional Semantic Models

Pablo Gamallo
2018 Machine Learning and Knowledge Extraction  
In this article, we define the outlier detection task and use it to compare neural-based word embeddings with transparent count-based distributional representations.  ...  In general, syntax-based models tend to perform better than those based on bag-of-words for this specific task. Similar experiments were carried out for Portuguese with similar results.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/make1010013 fatcat:qrxf444cd5drbbk24dheolbobm

Distinguishing Antonyms and Synonyms in a Pattern-based Neural Network

Kim Anh Nguyen, Sabine Schulte im Walde, Ngoc Thang Vu
2017 Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers  
In addition to the lexical and syntactic information, we successfully integrate the distance between the related words along the syntactic path as a new pattern feature.  ...  The results from classification experiments show that AntSyn-NET improves the performance over prior pattern-based methods.  ...  The research was supported by the Ministry of Education and Training of the Socialist Republic of Vietnam (Scholarship 977/QD-BGDDT; Kim-Anh Nguyen), the DFG Collaborative Research Centre SFB 732 (Kim-Anh  ... 
doi:10.18653/v1/e17-1008 dblp:conf/eacl/NguyenWV17 fatcat:4ak2gw3yjrdlbkomgwxioudpve

A Neural Network Model for Efficient Antonymy-Synonymy Classification by Exploiting Co-occurrence Contexts and Word-Structure Patterns

Van-Tan Bui, University of Economic and Technical Industries, Phuong-Thai Nguyen, Van-Lam Pham, Thanh-Quy Ngo, VNU University of Engineering and Technology, Institute of Linguistics, Vietnam Academy of Social Sciences, Thai Nguyen University
2020 International Journal of Intelligent Engineering and Systems  
This task is hard because antonyms and synonyms tend to occur in highly similar contexts. Recent studies often focus on exploiting densevector representations of words to deal with this problem.  ...  Antonymy and synonymy are basic semantic relations between words. Automatically distinguishing between antonymy and synonymy is an important task in natural language processing.  ...  In the unsupervised approach, distributional measures are used to distinguish synonymy from antonymy in an unsupervised manner.  ... 
doi:10.22266/ijies2020.0229.15 fatcat:2h5wngxbf5axhb4z2jxoz4kl7a

Distinguishing Antonyms and Synonyms in a Pattern-based Neural Network [article]

Kim Anh Nguyen and Sabine Schulte im Walde and Ngoc Thang Vu
2017 arXiv   pre-print
In addition to the lexical and syntactic information, we successfully integrate the distance between the related words along the syntactic path as a new pattern feature.  ...  The results from classification experiments show that AntSynNET improves the performance over prior pattern-based methods.  ...  The research was supported by the Ministry of Education and Training of the Socialist Republic of Vietnam (Scholarship 977/QD-BGDDT; Kim-Anh Nguyen), the DFG Collaborative Research Centre SFB 732 (Kim-Anh  ... 
arXiv:1701.02962v1 fatcat:iswc47dgbbdito2vl2hz2u25ge

Entity Type Recognition Using an Ensemble of Distributional Semantic Models to Enhance Query Understanding

Walid Shalaby, Khalifeh Al Jadda, Mohammed Korayem, Trey Grainger
2016 2016 IEEE 40th Annual Computer Software and Applications Conference (COMPSAC)  
Moreover, we achieve micro-averaged F 1 score of 97% using the proposed distributional representations ensemble.  ...  We employ distributional semantic representations of query entities through two models: 1) contextual vectors generated from encyclopedic corpora like Wikipedia, and 2) high dimensional word embedding  ...  After word2vec produces word distributional vectors, word synonymy vectors of search entities are generated as described in Section III.D.  ... 
doi:10.1109/compsac.2016.109 dblp:conf/compsac/ShalabyAKG16 fatcat:26qwomj5yrhf5fvkk5gs62v4ge
« Previous Showing results 1 — 15 out of 6,155 results