Abstract
The long-tail phenomenon of word sense distribution in linguistics causes Word Sense Disambiguation (WSD) to face both head senses with a large number of samples and tail senses with only a few samples. Traditional recognition methods are suitable for head senses with sufficient training samples, but they cannot effectively deal with tail senses. Inspired by the diverse memory and recognition abilities of children’s linguistic behavior, we propose a bi-matching mechanism approach for WSD. Considering that tail senses are often presented in the form of fixed collocations, a collocation feature matching method suitable for tail senses is designed; the traditional definition matching method is used for head senses; finally, the two matching methods are combined to construct a WSD model with the bi-matching mechanism (called Bi-MWSD). Bi-MWSD can effectively combat the difficulty of identifying the tail senses due to insufficient training samples. The experiments are implemented in the standard English all-words WSD evaluation framework and the training data augmented evaluation framework. The experimental results outperform the baseline models and achieve state-of-the-art performance under the data augmentation evaluation framework.
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
Similar content being viewed by others
References
Navigli, R., Camacho-Collados, J., Raganato, A.: Word sense disambiguation: a unified evaluation framework and empirical comparison. In: EACL (2017)
Navigli, R.: Word sense disambiguation: a survey. ACM Comput. Surv. 41, 1–69 (2009)
Bevilacqua, M., Pasini, T., Raganato, A., Navigli, R.: Recent trends in word sense disambiguation: a survey. In: IJCAI (2021)
Neale, S., Gomes, L.-M., Agirre, E., Lacalle, O.-L., Branco, A.-H.: Word sense-aware machine translation: including senses as contextual features for improved translation models. In: LREC (2016)
Rios Gonzales, A., Mascarell, L., Sennrich, R.: Improving word sense disambiguation in neural machine translation with sense embeddings. In: WMT (2017)
Dewadkar, D.-A., Haribhakta, Y.-V., Kulkarni, P.-A., Balvir, P.-D.: Unsupervised word sense disambiguation in natural language understanding. In: ICAI (2010)
Mills, M.-T., Bourbakis, N.-G.: Graph-based methods for natural language processing and understanding-a survey and analysis. IEEE Trans. Syst. Man Cybern. Syst. 44, 59–71 (2014)
Li, W., Madabushi, H.-T., Lee, M.-G.: UoB_UK at SemEval 2021 Task 2: Zero-shot and few-shot learning for multi-lingual and cross-lingual word sense disambiguation. In: SEMEVAL (2021)
Kumar, S., Jat, S., Saxena, K., Talukdar, P.-P.: Zero-shot word sense disambiguation using sense definition embeddings. In: ACL (2019)
Blevins, T., Zettlemoyer, L.: Moving down the long tail of word sense disambiguation with gloss informed bi-encoders. In: ACL (2020)
Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)
Huang, L., Sun, C., Qiu, X., Huang, X.: GlossBERT: BERT for word sense disambiguation with gloss knowledge. In: EMNLP (2019)
Holla, N., Mishra, P., Yannakoudakis, H., Shutova, E.: Learning to learn to disambiguate: meta-learning for few-shot word sense disambiguation. In: EMNLP (2020)
Du, Y., Holla, N., Zhen, X., Snoek, C.-G., Shutova, E.: Meta-learning with variational semantic memory for word sense disambiguation. In: ACL (2021)
Ibuka, M.: Kindergarten is Too Late!. Souvenir Press, London (1977)
Chen, H., Xia, M., Chen, D.: Non-parametric few-shot learning for word sense disambiguation. In: NAACL (2021)
Yuan, D., Richardson, J., Doherty, R., Evans, C., Altendorf, E.: Semi-supervised word sense disambiguation with neural models. In: COLING (2016)
Raganato, A., Bovi, C.-D., Navigli, R.: Neural sequence learning models for word sense disambiguation. In: EMNLP (2017)
Le, M.-N., Postma, M., Urbani, J., Vossen, P.: A Deep dive into word sense disambiguation with LSTM. In: COLING (2018)
Kågebäck, M., Salomonsson, H.: Word sense disambiguation using a bidirectional LSTM. In: COLING (2016)
Scarlini, B., Pasini, T., Navigli, R.: SensEmBERT: context-enhanced sense embeddings for multilingual word sense disambiguation. In: AAAI (2020)
Hadiwinoto, C., Ng, H.-T., Gan, W.-C.: Improved word sense disambiguation using pre-trained contextualized word representations. In: EMNLP (2019)
Du, J., Qi, F., Sun, M.: Using BERT for word sense disambiguation. arXiv:1909.08358 (2019)
Luo, F., Liu, T., Xia, Q., Chang, B., Sui, Z.: Incorporating glosses into neural word sense disambiguation. In: ACL (2018)
Fernandez, A.-D., Stevenson, M., Martínez-Romo, J., Araujo, L.: Co-occurrence graphs for word sense disambiguation in the biomedical domain. Artif. Intell. Med. 87, 9–19 (2018)
Scarlini, B., Pasini, T., Navigli, R.: With more contexts comes better performance: contextualized sense embeddings for all-round word sense disambiguation. In: EMNLP (2020)
Dongsuk, O., Kwon, S., Kim, K., Ko, Y.: Word sense disambiguation based on word similarity calculation using word vector representation from a knowledge-based graph. In: COLING (2018)
Pasini, T.: The knowledge acquisition bottleneck problem in multilingual word sense disambiguation. In: IJCAI (2020)
Kingma, D.-P., Ba, J.: Adam: A Method for Stochastic Optimization. CoRR, abs/1412.6980 (2015)
Pradhan, S., Loper, E., Dligach, D., Palmer, M.: SemEval-2007 Task 2017: English lexical sample. In: SRL and All Words, Fourth International Workshop on Semantic Evaluations (2007)
Edmonds, P., Cotton, S.: SENSEVAL-2: Overview. *SEMEVAL (2001)
Snyder, B., Palmer, M.: The English all-words task. In: ACL (2004)
Navigli, R., Jurgens, D., Vannella, D.: SemEval-2013 task 12: multilingual word sense disambiguation. In: *SEMEVAL (2013)
Moro, A., Navigli, R.: SemEval-2015 Task 13: multilingual all-words sense disambiguation and entity linking. In: *SEMEVAL (2015)
Fellbaum, C.-D.: WordNet: An Electronic Lexical Database. Language. MIT Press, Cambridge (2000)
Loureiro, D., Jorge, A.-M.: Language modelling makes sense: propagating representations through wordnet for full-coverage word sense disambiguation. In: ACL (2019)
Wang, M., Wang, Y.: A synset relation-enhanced framework with a try-again mechanism for word sense disambiguation. In: EMNLP (2020)
Bevilacqua, M., Navigli, R.: Breaking Through the 80% Glass Ceiling: Raising the State of the Art in Word Sense Disambiguation by Incorporating Knowledge Graph Information. ACL (2020)
Berend, G.: Sparsity Makes Sense: Word Sense Disambiguation Using Sparse Contextualized Word Representations. EMNLP (2020)
Wang, M., Zhang, J., Wang, Y.: Enhancing the Context Representation in Similarity-based Word Sense Disambiguation. EMNLP (2021)
Song, Y., Ong, X.C., Ng, H.T., Lin, Q.: Improved Word Sense Disambiguation with Enhanced Sense Representations. EMNLP (2021)
Conia, S., Navigli, R.: Framing Word Sense Disambiguation as a Multi-Label Problem for Model-Agnostic Knowledge Integration. EACL (2021)
Wang, M., Wang, Y.: Word Sense Disambiguation: Towards Interactive Context Exploitation from Both Word and Sense Perspectives. ACL (2021)
Acknowledgements
Our work is supported by the National Natural Science Foundation of China (61976154), the National Key R &D Program of China (2019YFC1521200), the State Key Laboratory of Communication Content Cognition, People’s Daily Online (No. A32003), and the National Natural Science Foundation of China (No. 62106176).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, J., He, R., Guo, F. (2023). Bi-matching Mechanism to Combat Long-tail Senses of Word Sense Disambiguation. In: Amini, MR., Canu, S., Fischer, A., Guns, T., Kralj Novak, P., Tsoumakas, G. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2022. Lecture Notes in Computer Science(), vol 13714. Springer, Cham. https://doi.org/10.1007/978-3-031-26390-3_36
Download citation
DOI: https://doi.org/10.1007/978-3-031-26390-3_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26389-7
Online ISBN: 978-3-031-26390-3
eBook Packages: Computer ScienceComputer Science (R0)