Learning human-like knowledge by singular value decomposition: a progress report
NIPS '97 Proceedings of the 1997 conference on Advances in neural information processing systems 10
A vector space model for automatic indexing
Communications of the ACM
Modern Information Retrieval
Introduction to Modern Information Retrieval
Introduction to Modern Information Retrieval
Mining the Web for Synonyms: PMI-IR versus LSA on TOEFL
EMCL '01 Proceedings of the 12th European Conference on Machine Learning
Document clustering based on non-negative matrix factorization
Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval
Applied morphological processing of English
Natural Language Engineering
Automatic retrieval and clustering of similar words
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
Antonymy and conceptual vectors
COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Corpus-based Learning of Analogies and Semantic Relations
Machine Learning
Improvements in automatic thesaurus extraction
ULA '02 Proceedings of the ACL-02 workshop on Unsupervised lexical acquisition - Volume 9
Similarity of Semantic Relations
Computational Linguistics
Finding synonyms using automatic word alignment and measures of distributional similarity
COLING-ACL '06 Proceedings of the COLING/ACL on Main conference poster sessions
Negation, contrast and contradiction in text processing
AAAI'06 Proceedings of the 21st national conference on Artificial intelligence - Volume 1
A uniform approach to analogies, synonyms, antonyms, and associations
COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
A study on similarity and relatedness using distributional and WordNet-based approaches
NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Computing semantic relatedness using Wikipedia-based explicit semantic analysis
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Identifying synonyms among distributionally similar words
IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 1 - Volume 1
Multi-prototype vector-space models of word meaning
HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
From frequency to meaning: vector space models of semantics
Journal of Artificial Intelligence Research
Translingual document representations from discriminative projections
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Learning discriminative projections for text similarity measures
CoNLL '11 Proceedings of the Fifteenth Conference on Computational Natural Language Learning
Hi-index | 0.00 |
Existing vector space models typically map synonyms and antonyms to similar word vectors, and thus fail to represent antonymy. We introduce a new vector space representation where antonyms lie on opposite sides of a sphere: in the word vector space, synonyms have cosine similarities close to one, while antonyms are close to minus one. We derive this representation with the aid of a thesaurus and latent semantic analysis (LSA). Each entry in the thesaurus -- a word sense along with its synonyms and antonyms -- is treated as a "document," and the resulting document collection is subjected to LSA. The key contribution of this work is to show how to assign signs to the entries in the co-occurrence matrix on which LSA operates, so as to induce a subspace with the desired property. We evaluate this procedure with the Graduate Record Examination questions of (Mohammed et al., 2008) and find that the method improves on the results of that study. Further improvements result from refining the subspace representation with discriminative training, and augmenting the training data with general newspaper text. Altogether, we improve on the best previous results by 11 points absolute in F measure.