Abstract
Word sense embeddings are vector representations of polysemous words – words with multiple meanings. These induced sense embeddings, however, do not necessarily correspond to any dictionary senses of the word. To overcome this, we propose a method to find new sense embeddings with known meaning. We term this method refitting, as the new embedding is fitted to model the meaning of a target word in an example sentence. The new lexically refitted embeddings are learnt using the probabilities of the existing induced sense embeddings, as well as their vector values. Our contributions are threefold: (1) The refitting method to find the new sense embeddings; (2) a novel smoothing technique, for use with the refitting method; and (3) a new similarity measure for words in context, defined by using the refitted sense embeddings. We show how our techniques improve the performance of the Adaptive Skip-Gram sense embeddings for word similarly evaluation; and how they allow the embeddings to be used for lexical word sense disambiguation.
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.
As this part of our method is used with both the unsupervised senses and the lexical senses, referred to as \(\textbf{u}\) and \(\textbf{l}\) respectively in other parts of the paper, here we use a general sense \(\textbf{s}\) to avoid confusion.
- 2.
- 3.
- 4.
It should be noted, though, that the number of meanings is not normally distributed [23].
References
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv:1301.3781 (2013)
Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP 2014), pp. 1532–1543 (2014)
Reisinger, J., Mooney, R.J.: Multi-prototype vector-space models of word meaning. In: Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pp. 109–117. Association for Computational Linguistics (2010)
Huang, E.H., Socher, R., Manning, C.D., Ng, A.Y.: Improving word representations via global context and multiple word prototypes. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers-Vol. 1, pp. 873–882. Association for Computational Linguistics (2012)
Tian, F., et al.: A probabilistic model for learning multi-prototype word embeddings. In: COLING, pp. 151–160 (2014)
Bartunov, S., Kondrashkin, D., Osokin, A., Vetrov, D.P.: Breaking sticks and ambiguities with adaptive skip-gram. CoRR abs/1502.07257 (2015)
Miller, G.A.: Wordnet: a lexical database for English. Commun. ACM 38, 39–41 (1995)
Véronis, J.: A study of polysemy judgements and inter-annotator agreement. In: Programme and Advanced Papers of the Senseval workshop, pp. 2–4 (1998)
Iacobacci, I., Pilehvar, M.T., Navigli, R.: Sensembed: learning sense embeddings for word and relational similarity. In: Proceedings of ACL, pp. 95–105 (2015)
Moro, A., Raganato, A., Navigli, R.: Entity linking meets word sense disambiguation: a unified approach. Trans. Assoc. Comput. Linguist. 2, 231–244 (2014)
Chen, X., Liu, Z., Sun, M.: A unified model for word sense representation and disambiguation. In: EMNLP, pp. 1025–1035. Citeseer (2014)
Agirre, E., Martínez, D., De Lacalle, O.L., Soroa, A.: Evaluating and optimizing the parameters of an unsupervised graph-based WSD algorithm. In: Proceedings of the First Workshop on Graph Based Methods for Natural Language Processing, Association for Computational Linguistics, pp. 89–96 (2006)
Agirre, E., Soroa, A.: Semeval-2007 task 02: evaluating word sense induction and discrimination systems. In: Proceedings of the 4th International Workshop on Semantic Evaluations. SemEval 2007, Stroudsburg, PA, USA, pp. 7–12. Association for Computational Linguistics (2007)
Nocedal, J.: Updating quasi-newton matrices with limited storage. Math. Comput. 35, 773–782 (1980)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111–3119 (2013)
Mikolov, T., Yih, W.t., Zweig, G.: Linguistic regularities in continuous space word representations. In: HLT-NAACL, pp. 746–751 (2013)
Bengio, Y., Ducharme, R., Vincent, P., Janvin, C.: A neural probabilistic language model. J. Mach. Learn. Res. 3, 137–186 (2003)
Rosenfeld, R.: Two decades of statistical language modeling: where do we go from here? Proc. IEEE 88, 1270–1278 (2000)
Zipf, G.: Human Behavior and the Principle of Least Effort: An Introduction to Human Ecology. Addison-Wesley Press, Cambridge (1949)
Kilgarriff, A.: How dominant is the commonest sense of a word? In: Sojka, P., Kopeček, I., Pala, K. (eds.) TSD 2004. LNCS (LNAI), vol. 3206, pp. 103–111. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-30120-2_14
Bezanson, J., Edelman, A., Karpinski, S., Shah, V.B.: Julia: a fresh approach to numerical computing. SIAM Rev. 59, 65–98 (2014)
Neelakantan, A., Shankar, J., Passos, A., McCallum, A.: Efficient non-parametric estimation of multiple embeddings per word in vector space. arXiv preprint arXiv:1504.06654 (2015)
Zipf, G.K.: The meaning-frequency relationship of words. J. Gen. Psychol. 33, 251–256 (1945)
Tengi, R.I.: Design and implementation of the WordNet lexical database and searching software. In: WordNet: An Electronic Lexical Database, p. 105. The MIT Press, Cambridge (1998)
Navigli, R., Litkowski, K.C., Hargraves, O.: Semeval-2007 task 07: coarse-grained English all-words task. In: Proceedings of the 4th International Workshop on Semantic Evaluations. SemEval 2007, Stroudsburg, PA, USA, Association for Computational Linguistics, pp. 30–35 (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 Springer Nature Switzerland AG
About this paper
Cite this paper
White, L., Togneri, R., Liu, W., Bennamoun, M. (2023). Finding Word Sense Embeddings of Known Meaning. In: Gelbukh, A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2018. Lecture Notes in Computer Science, vol 13397. Springer, Cham. https://doi.org/10.1007/978-3-031-23804-8_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-23804-8_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23803-1
Online ISBN: 978-3-031-23804-8
eBook Packages: Computer ScienceComputer Science (R0)