Clustering for clarity: improving word sense disambiguation through multilevel analysis

• Autorzy: Dubey Shiv Kishan , Kohli Narendra

Identyfikatory

DOI

10.7494/csci.2024.25.2.5844

• Języki publikacji: EN

Abstrakty

EN

Existing Word Sense Disambiguation (WSD) techniques have limits in exploring word-context relationships since they only deal with the effective use of word embedding, lexical-based information via WordNet, or the precision of clustering algorithms. In order to overcome this limitation, the study suggests a unique hybrid methodology that makes use of context embedding based on center-embedding in order to capture semantic subtleties and utilizing with atwo-level K-means clustering algorithm. Such generated context embedding, producing centroids that serve as representative points for semantic information inside clusters. Additionally, go with such captured cluster- centres in the nested levels of clustering process, locate groups of linked context words and categorize them according to their word meanings that effectively manage polysemy/homonymy as well as detect minute differences in meaning. Our proposed approach offers a substantial improvement over traditional WSD methods by harnessing the power of center-embedding in context representation, enhancingthe precision of clustering and ultimately overcoming existing limitations incontext-based sense disambiguation.

Słowa kluczowe

EN

embeddings; center embedding; multilevel clustering; word sense disambiguation; WSD; polysemy; homonymy

• Wydawca: Wydawnictwa AGH
• Czasopismo: Computer Science
• Rocznik: 2024
• Tom: T. 25 (2)
• Strony: 277--300
• Opis fizyczny: Bibliogr. 21 poz., rys., tab.

Twórcy

autor

Dubey Shiv Kishan

• Harcourt Butler Technical University, Kanpur

autor

Kohli Narendra

• Department of Computer Science, HBTU Kanpur, Uttar Pradesh

Bibliografia

• [1] Agirre E., L´opez de Lacalle O., Soroa A.: Random Walks for Knowledge-Based Word Sense Disambiguation, Computational Linguistics, vol. 40(1), pp. 57–84, 2014. doi: 10.1162/COLI a 00164.
• [2] AlMousa M., Benlamri R., Khoury R.: A novel word sense disambiguation approach using WordNet knowledge graph, Computer Speech & Language, vol. 74, 101337, 2022. doi: 10.1016/j.csl.2021.101337.
• [3] Anaya-S´anchez H., Pons-Porrata A., Berlanga-Llavori R.: TKB-UO: Using Sense Clustering for WSD. In: SemEval ’07: Proceedings of the 4th International Workshop on Semantic Evaluations, pp. 322–325, 2007. doi: 10.3115/1621474.1621544.
• [4] Berahmand K., Li Y., Xu Y.: A Deep Semi-Supervised Community Detection Based on Point-Wise Mutual Information, IEEE Transactions on Computational Social Systems, vol. 11(3), pp. 3444–3456, 2023. doi: 10.1109/TCSS.2023.3327810.
• [5] Bhingardive S., Singh D., Rudramurthy V., Redkar H., Bhattacharyya P.: Unsupervised most frequent sense detection using word embeddings. In: Proceedings of the 2015 conference of the North American Chapter of the Association for Computational Linguistics: Human language technologies, pp. 1238–1243, 2015. doi: 10.3115/v1/n15-1132.
• [6] Chifu A.G., Hristea F., Mothe J., Popescu M.: Word sense discrimination in information retrieval: A spectral clustering-based approach, Information Processing & Management, vol. 51(2), pp. 16–31, 2015. doi: 10.1016/j.ipm.2014.10.007.
• [7] Dubey S., Kohli N.: A Multilevel Center Embedding approach for Sentence Similarity having Complex structures. In: 2023 World Conference on Communication & Computing (WCONF), pp. 1–8, 2023. doi: 10.1109/wconf58270.2023.10235102.
• [8] Guerrieri A., Rahimian F., Girdzijauskas S., Montresor A.: Tovel: Distributed graph clustering for word sense disambiguation. In: 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW), pp. 623–630, IEEE, 2016. doi: 10.1109/icdmw.2016.0094.
• [9] Huang L., Sun C., Qiu X., Huang X.: GlossBERT: BERT for word sense disambiguation with gloss knowledge. In: K. Inui, J. Jiang, V. Ng, X. Wan (eds.), Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 3509–3514, 2019. doi: 10.18653/v1/d19-1355.
• [10] Le A.C., Shimazu A., Huynh V.N., Nguyen L.M.: Semi-supervised learning integrated with classifier combination for word sense disambiguation, Computer Speech & Language, vol. 22(4), pp. 330–345, 2008. doi: 10.1016/j.csl.2007.11.001.
• [11] Li X., Qing S., Zhang H., Wang T., Yang H.: Kernel methods for word sense disambiguation, Artificial Intelligence Review, vol. 46, pp. 41–58, 2016. doi: 10.1007/s10462-015-9455-5.
• [12] Lyashevskaya O., Mitrofanova O., Grachkova M., Romanov S., Shimorina A., Shurygina A.: Automatic Word Sense Disambiguation and Construction Identification Based on Corpus Multilevel Annotation. In: Text, Speech and Dialogue: 14th International Conference, TSD 2011, Pilsen, Czech Republic, September 1–5, 2011. Proceedings 14, pp. 80–90, Springer, 2011. doi: 10.1007/978-3-642- 23538-2 11.
• [13] Mart´ın T., Berlanga-Llavori R.: A clustering-based approach for unsupervised word sense disambiguation, Procesamiento del Lenguaje Natural, vol. 49, pp. 49–56, 2012.
• [14] Miller G.A., Chodorow M., Landes S., Leacock C., Thomas R.G.: Using a semantic concordance for sense identification. In: HLT ’94: Proceedings of the workshop on Human Language Technology, 1994. doi: 10.3115/1075812.1075866.
• [15] Niu Z.Y., Ji D.H., Tan C.L.: Learning model order from labeled and unlabeled data for partially supervised classification, with application to word sense disambiguation, Computer Speech & Language, vol. 21(4), pp. 609–619, 2007. doi: 10.1016/j.csl.2007.02.001.
• [16] Pasini T., Scozzafava F., Scarlini B.: CluBERT: A cluster-based approach for learning sense distributions in multiple languages. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 4008–4018, 2020. doi: 10.18653/v1/2020.acl-main.369.
• [17] Patil A.P., Ramteke R., Bhavsar R., Darbari H.: Graph-Based Algorithm for Word Sense Disambiguation: A Performance and Comparison, Sambodhi, vol. 44(03), pp. 77–79, 2021.
• [18] Pelevina M., Arefyev N., Biemann C., Panchenko A.: Making sense of word embeddings, arXiv preprint arXiv:170803390, 2017. doi: 10.48550 / arXiv.1708.03390.
• [19] Seo H.C., Chung H., Rim H.C., Myaeng S.H., Kim S.H.: Unsupervised word sense disambiguation using WordNet relatives, Computer Speech & Language, vol. 18(3), pp. 253–273, 2004. doi: 10.1016/j.csl.2004.05.004.
• [20] Shirai K., Nakamura M.: JAIST: Clustering and classification based approaches for Japanese WSD. In: K. Erk, C. Strapparava (eds.), Proceedings of the 5th International Workshop on Semantic Evaluation, pp. 379–382, Association for Computational Linguistics, Uppsala, Sweden, 2010. https://aclanthology.org/ S10-1085.
• [21] Vaishnav Z.B., Sajja P.S.: Knowledge-Based Approach for Word Sense Disambiguation Using Genetic Algorithm for Gujarati. In: S.C. Satapathy, A. Joshi (eds.), Information and Communication Technology for Intelligent Systems. Smart Innovation, Systems and Technologies, vol. 1, pp. 485–494, Springer, Singapore, 2019. doi: 10.1007/978-981-13-1742-2 48.

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).