Abstract
Antonymy and Synonymy are paradigmatic relations which are in the core problems of language. Distinguishing antonyms from synonyms is a key task to achieve high performance in natural language processing systems. Distinguishing between antonyms and synonyms is a hard problem because the co-occurrence distributions of the antonyms or synonyms tend to be highly similar. On the other hand, this issue has been thoroughly studied in English. However, it has not been effectively addressed for Vietnamese. Compared to English, Vietnamese has its own word-level characteristics that indicate the synonymous or antonymous relation. In this paper, we introduce a framework which exploits exhaustively special Vietnamese features to distinguish between antonyms from synonyms. We propose a deep neural network model (ViASNet) that can utilize not only lexico-syntactic information captured from the context of word pairs in a corpus but also its word-level features, and distribution features as well. The experimental results show that the proposed method is effective. Furthermore, our method achieved high performance in comparison to several the state of the art methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
UNK denotes to Vietnamese syllables that don’t have any corresponding English words.
- 3.
- 4.
Collected from vietnamese Wikipedia and https://baomoi.com/.
- 5.
References
Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. TACL 5, 135–146 (2017). http://dblp.uni-trier.de/db/journals/tacl/tacl5.html#BojanowskiGJM17
Bordag, S.: A comparison of co-occurrence and similarity measures as simulations of context. In: Gelbukh, A. (ed.) CICLing 2008. LNCS, vol. 4919, pp. 52–63. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-78135-6_5
Charles, W.G., Miller, G.A.: Contexts of antonymous adjectives. Appl. Psycholinguist. 10, 357–375 (1989)
Santus, E., Lu, Q., Lenci, A., Huang, C.: Unsupervised antonym-synonym discrimination in vector space. In: The First Italian Conference on Computational Linguistics CLiC-it (2014)
Fellbaum, C.: Co-occurrence and antonymy. Int. J. Lexicogr. 8(4), 281–303 (1995)
Fundel, K., Küffner, R., Zimmer, R.: Relex - relation extraction using dependency parse trees. Bioinformatics 23(3), 365–371 (2007)
Lam, P.V.: Study antonyms in Vietnamese. Doctoral thesis (2019)
Lin, D., Zhao, S., Qin, L., Zhou, M.: Identifying synonyms among distributionally similar words. In: Proceedings of the 18th International Joint Conference on Artificial Intelligence (IJCAI-2003), pp. 1492–1493 (2003)
Lyons, J.: Semantics. Cambridge University Press, Cambridge (1977)
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arxiv:1301.3781 (2013)
Mohammad, S., Dorr, B.J., Hirst, G., Turney, P.D.: Computing lexical contrast. Comput. Linguist. 39(3), 555–590 (2013)
Mrksic, N., et al.: Semantic specialisation of distributional word vector spaces using monolingual and cross-lingual constraints. CoRR (2017)
Murphy, L.M.: Semantic Relations and the Lexicon. Cambridge University Press, Cambridge (2003)
Ngo, T.V., Ha, T.L., Nguyen, P.T., Nguyen, L.M.: Combining advanced methods in Japanese-Vietnamese neural machine translation. In: KSE, pp. 318–322. IEEE (2018)
Nguyen, D.Q., Dras, M., Johnson, M.: An empirical study for Vietnamese dependency parsing. In: ALTA, pp. 143–149. ACL (2016)
Nguyen, K.A., Walde, S.S., Vu, N.T.: Integrating distributional lexical contrast into word embeddings for antonym-synonym distinction. In: The 54th Annual Meeting of the Association for Computational Linguistics, p. 454 (2016)
Nguyen, K.A., Walde, S.S., Vu, N.T.: Distinguishing antonyms and synonyms in a pattern-based neural network. In: EACL, pp. 76–85. Association for Computational Linguistics (2017)
Nguyen, K.A., Walde, S.S., Vu, N.T.: Introducing two Vietnamese datasets for evaluating semantic models of (dis-)similarity and relatedness. In: NAACL-HLT, pp. 199–205. Association for Computational Linguistics (2018)
Nguyen, P.T., Pham, V.L., Nguyen, H.A., Vu, H.H., Tran, N.A., Truong, T.T.H.: A two-phase approach for building Vietnamese wordnet. In: The 8th Global Wordnet Conference, pp. 259–264 (2015)
Ono, M., Miwa, M., Sasaki, Y.: Word embedding-based antonym detection using thesauri and distributional information. In: HLT-NAACL, pp. 984–989 (2015)
Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: EMNLP, vol. 14, pp. 1532–1543 (2014)
Roth, M., im Walde, S.S.: Combining word patterns and discourse markers for paradigmatic relation classification. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pp. 524–530. Association for Computational Linguistics (2014)
Scheible, S., im Walde, S.S., Springorum, S.: Uncovering distributional differences between synonyms and antonyms in a word space model. In: IJCNLP, pp. 489–497. Asian Federation of Natural Language Processing/ACL (2013)
Tan, B.V., Thai, N.P., Lam, P.V.: Construction of a word similarity dataset and evaluation of word similarity techniques for Vietnamese. In: KSE, pp. 65–70. IEEE (2017)
Tan, B.V., Thai, N.P., Thuan, N.M.: Enhancing performance of lexical entailment recognition for Vietnamese based on exploiting lexical structure features. In: KSE, pp. 341–346. IEEE (2018)
im Walde, S.S., Köper, M.: Pattern-based distinction of paradigmatic relations for German nouns, verbs, adjectives. In: Gurevych, I., Biemann, C., Zesch, T. (eds.) GSCL 2013. LNCS (LNAI), vol. 8105, pp. 184–198. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40722-2_19
Acknowledgments
This paper is a part of project number KHCN-TB.23X/13-18 which is led by Assoc. Prof. Ngo Thanh Quy and funded by Vietnam National University, Hanoi under the Science and Technology Program for the Sustainable Development of Northwest Region.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Tan, B.V., Thai, N.P., Lam, P.V., Quy, D.K. (2020). Antonyms-Synonyms Discrimination Based on Exploiting Rich Vietnamese Features. In: Nguyen, LM., Phan, XH., Hasida, K., Tojo, S. (eds) Computational Linguistics. PACLING 2019. Communications in Computer and Information Science, vol 1215. Springer, Singapore. https://doi.org/10.1007/978-981-15-6168-9_31
Download citation
DOI: https://doi.org/10.1007/978-981-15-6168-9_31
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-6167-2
Online ISBN: 978-981-15-6168-9
eBook Packages: Computer ScienceComputer Science (R0)