UIJRT » United International Journal for Research & Technology

Simplified Natural Language Processing and Discrimination in Antonyms-Synonyms Word Structure in a Neural Network Approach to Exploit Lexico-Semantic Pattern

Maksuda Sultana and Dr. Ana Romina A, Miguel
Keywords: Neural language processing, Semantic relation classification, Antonyms-synonyms Distinction.

Cite ➜

Sultana, M. and Miguel, A.R.A., 2020. Simplified Natural Language Processing and Discrimination in Antonyms-Synonyms Word Structure in a Neural Network Approach to Exploit Lexico-Semantic Pattern. United International Journal for Research & Technology (UIJRT), 2(2), pp.06-17.

Abstract

To get high efficiency or high yielding in NLP system the vital challenge is to distinguish between antonym and synonym. By using lexico-syntactic patterns in pattern-based models, which are string-matching patterns based on lexical and syntactic structure, we exploiting to represent the distinguish between antonyms and synonyms word pairs as vector representation in Arabic word structure. It is very difficult to make automatic distinguish between antonymy-synonymy in NLP system because of they have a tendency to occur in similar contexts. I intend a 2-step novel process that exploit lexico-semantic pattern to distinguish antonymy-synonymy from syntactic parse tress. The experiment result shows the improvement of the performance over prior pattern-based method.

References

  1. Lyons, “Semantics”, Cambridge University Press, volume 1, 1977.
  2. G. Charles and G.A. Miller, “Contexts of antonymous adjectives”, Applied Psycholinguistics, pp.357-375, 1989.
  3. Fellbaum, “Co-Occurrence and Antonymy”, International Journal of Lexicography, pp.281-303, 1995.
  4. Turney, P. D., and Pantel, P. 2010. From frequency to meaning: Vector space models of semantics. J. Artif. Intell. Res. 37:141–188.
  5. Mikolov, T.; Chen, K.; Corrado, G.; and Dean, J. 2013a. Efficient estimation of word representations in vector space. CoRR abs/1301.3781.
  6. Mikolov, T.; Sutskever, I.; Chen, K.; Corrado, G. S.; and Dean, J. 2013b. Distributed representations of words and phrases and their compositionality. In NIPS, 3111–3119.
  7. Pennington, J.; Socher, R.; and Manning, C. D. 2014. Glove: Global vectors for word representation. In EMNLP, 1532– 1543. ACL.
  8. Scheible, S.; Schulte im Walde, S.; and Springorum, S. 2013. Uncovering distributional differences between synonyms and antonyms in a word space model. In IJCNLP, 489–497. Asian Federation of Natural Language Processing / ACL.
  9. Adel, H., and Sch¨utze, H. 2014. Using mined coreference chains as a resource for a semantic task. In EMNLP, 1447– 1452. ACL.
  10. Nguyen, K. A.; Schulte im Walde, S.; and Vu, N. T. 2016. Integrating distributional lexical contrast into word embeddings for antonym-synonym distinction. In ACL (2). The Association for Computer Linguistics.
  11. Pham, N. T.; Lazaridou, A.; and Baroni, M. 2015. A multitask objective to inject lexical contrast into distributional semantics. In ACL (2), 21–26. The Association for Computer Linguistics.
  12. Ono, M.; Miwa, M.; and Sasaki, Y. 2015. Word embedding based antonym detection using thesauri and distributional information. In HLT-NAACL,
  13. Lin, S. Zhao, L. Qin, and M. Zhou, “Identifying synonyms among distributionally similar words”, In: Proc. of IJCAI, pp.1492-1493, 2003.
  14. Mohammad, B.J Dorr, G. Hirst, and P.D. Turney, “Computing lexical contrast”, Computational Linguistics, Vol. 39, No.3, pp.555-590, 2013.
  15. D. Turney, “A uniform approach to analogies, synonyms, antonyms, and associations”, In: Proc. of COLING, pp.905-912, 2008.
  16. Scheible, S.S. im Walde, and S. Springorum, “Uncovering distributional differences between synonyms and antonyms in a word space model”, In: Proc. of IJCNLP, pp.489-497, 2013.
  17. [Roth and Schulte im Walde2014] Michael Roth and Sabine Schulte im Walde. 2014. Combining word patterns and discourse markers for paradigmatic relation classification. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL), pages 524–530, Baltimore, MD.
  18. Scheible et al.2013] Silke Scheible, Sabine Schulte im Walde, and Sylvia Springorum. 2013. Uncovering distributional differences between synonyms and antonyms in a word space model. In Proceedings of the 6th International Joint Conference on Natural Language Processing (IJCNLP), pages 489–497, Nagoya, Japan.
  19. Mikolov, K. Chen, G. Corrado, and J. Dean, “Efficient estimation of word representations in vector space”, In: Proc. of ICLR, 2013.
  20. Mikolov, K. Chen, G. Corrado, and J. Dean, “Efficient estimation of word representations in vector space”, In: Proc. of ICLR, 2013.
  21. Pennington, R. Socher, and C.D. Manning, “Glove: Global vectors for word representation”, In: Proc. of EMNLP, Vol. 14, pp.1532-1543, 2014.
  22. Bojanowski, E. Grave, A. Joulin, and T. Mikolov, “Enriching word vectors with subword information”, In: Proc. of TACL 5, pp.135-146, 2017.
  23. Bojanowski, E. Grave, A. Joulin, and T. Mikolov, “Enriching word vectors with subword information”, In: Proc. of TACL 5, pp.135-146, 2017.
  24. Mrksic, I. Vulic, D. S´eaghdha, I. Leviant, R. Reichart, M. Gasic, A. Korhonen, and S.J. Young, “Semantic specialization of distributional word vector spaces using monolingual and cross-lingual constraints”, Transactions of the ACL, 2017.
  25. Santus, Q. Lu, A. Lenci, and C.R. Huang, “Unsupervised antonym-synonym discrimination in vector space”, In: Proc. of CLiC-it, 2014.
  26. Roth and S.S. im Walde, “Combining word patterns and discourse markers for paradigmatic relation classification”, In: Proc. of NAACL, pp. 524-530, 2014.
  27. T. Bui, P.T, Nguyen, and M.T. Nguyen, “Enhancing performance of lexical entailment recognition for Vietnamese based on exploiting lexical structure features”, In: Proc. of KSE, pp.341-346, 2018.
  28. Fundel, R. K¨uffner, and R. Zimmer, “Relex -relation extraction using dependency parse trees”, Bioinformatics, Vol. 23, No. 3, pp.365-371, 2007.
  29. Xu, L. Mou, G. Li, Y. Chen, H. Peng, and Z. Jin, “Classifying relations via long short term memory networks along shortest dependency paths”, In: Proc. of EMNLP, pp.1785-1794, 2015.
  30. Sadek, F. Chakkour, and F. Meziane, “Arabic Rhetorical Relations Extraction for Answering ‘Why’ and ‘How to’ Questions,” in Proceedings of the 17th International Conference on Applications of Natural Language Processing and Informati Systems, Berlin, Heidelberg, 2012, pp. 385– 390.
  31. Ibrahim and T. Elghazaly, “Arabic text summarization using Rhetorical Structure Theory,” in 2012 8th International Conference on Informatics and Systems (INFOS), 2012, p. NLP–34–NLP–38.
  32. A. Hearst, “Automatic acquisition of hyponyms from large text corpora,” in Proceedings of the 14th conference on Computational linguistics – Volume 2, Stroudsburg, PA, USA, 1992, pp. 539–545.
  33. Pantel and M. Pennacchiotti, “Espresso: leveraging generic patterns for automatically harvesting semantic relations,” in Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics, Stroudsburg, PA, USA, 2006, pp. 113–120.
  34. Wang, C. Thomas, A. Sheth, and V.Chan, “Pattern-based synonym and antonym extraction,” in Proceedings of the 48th Annual Southeast Regional Conference, New York, NY, USA, 2010, pp. 64:1–64:4.
  35. C. Can, H.Q. Le, Q.T. Ha, and N. Collier, “A richer-but-smarter shortest dependency path with attentive augmentation for relation extraction”, In: Proc. of NAACL-HLT(1), pp.2902-2912, 2019.
  36. Joshi, E. Choi, O. Levy, D.S. Weld, and L. Zettlemoyer, “pair2vec: Compositional word-pair embeddings for cross-sentence inference”, In: Proc. of NAACL, pp.3597- 3608, 2019.
  37. Dukes, K., Habash, N., 2010. Morphological annotation of Quranic Arabic. In: The 7th International Conference on Language Resources and Evaluation (LREC), Valletta, Malta, pp. 2530–2536.
  38. Adhima, M., 1972. Derasat li Osloob Al-Quraan Al-Karim. In: Arabic. Cairo, Egypt: Dar Al-Hadith.
  39. Elkateb, S., Black, W., Rodríguez, H., Alkhalifa, M., Vossen, P., Pease, A., & Fellbaum, C. (2006). Building a wordnet for Arabic. In Proceedings of The fifth international conference on Language Resources and Evaluation (LREC 2006).
  40. A. Nguyen, S.S. im Walde, and N.T. Vu, “Distinguishing antonyms and synonyms in a pattern-based neural network”, In: Proc. of EACL, pp.76-85, 2017.
  41. OMWEdit – The Integrated Open Multilingual WordNet Editing System
  42. Hochreiter and J. Schmidhuber, “Long short-term memory”, Neural computation, pp.1735-1780, 1997.
  43. Xu, L. Mou, G. Li, Y. Chen, H. Peng, and Z. Jin, “Classifying relations via long short term memory networks along shortest dependency paths”, In: Proc. of EMNLP, pp.1785-1794, 2015.
  44. A. Nguyen, S.S. im Walde, and N.T. Vu, “Distinguishing antonyms and synonyms in a pattern-based neural network”, In: Proc. of EACL, pp.76-85, 2017.
  45. Adhima, M., 1972. Derasat li Osloob Al-Quraan Al-Karim. In: Arabic. Cairo, Egypt: Dar Al-Hadith.
  46. A. Nguyen, S.S. im Walde, and N.T. Vu, “Integrating distributional lexical contrast into word embeddings for antonym-synonym distinction”, In: Proc. of NAACL, p. 454-459, 2016.
  47. Pennington, R. Socher, and C.D. Manning, “Glove: Global vectors for word representation”, In: Proc. of EMNLP, Vol. 14, pp.1532-1543, 2014.
  48. Bojanowski, E. Grave, A. Joulin, and T. Mikolov, “Enriching word vectors with subword information”, In: Proc. of TACL 5,
  49. Nguyen, K. A.; Schulte im Walde, S.; and Vu, N. T. 2016. Distinguishing Antonyms and Synonyms in a pattern based Neural Network. In ACL (2). The Association for Computer Linguistics.
  50. Muhammad Asif Ali,1 Yifang Sun,1 Xiaoling Zhou,1 Wei Wang,1,2 Xiang Zhao3-2019 Antonym-Synonym Classification Based on New Sub-Space Embeddings The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19).
Scroll to Top