{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:24:19Z","timestamp":1772119459172,"version":"3.50.1"},"reference-count":36,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T00:00:00Z","timestamp":1772064000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001691","name":"JSPS","doi-asserted-by":"publisher","award":["22K12161"],"award-info":[{"award-number":["22K12161"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"JSPS","doi-asserted-by":"publisher","award":["25K15242"],"award-info":[{"award-number":["25K15242"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>In semantic classification of katakana words using large language models and pre-trained language models, semantic divergences from original English meanings, such as those found in Wasei-Eigo which is Japanese-made English, and the inherent sense ambiguity in katakana words may affect model accuracy. To analyze the impact of these loanword semantic characteristics on classification accuracy, we created a large-scale dataset from the Balanced Corpus of Contemporary Written Japanese. We extracted 403,819 sentences covering 230 katakana words defined in dictionaries and suitable for word sense disambiguation tasks, and used the gpt-4.1-mini model to predict the meaning of the target words based on their context, to create annotation data. We then fine-tuned the pre-trained language model DeBERTa V3 with this data. We compared baseline and fine-tuned model accuracy, dividing data into four quadrants based on frequency and polysemy to conduct statistical analysis and explore strategies for improving accuracy. We also tested the hypothesis that high-frequency, low-polysemy words would achieve the highest accuracy, while low-frequency, high-polysemy words would achieve the lowest. As a result, the fine-tuned model showed an average accuracy improvement of approximately 53% compared to the baseline model. As hypothesized, high-frequency, low-polysemy words achieved the highest accuracy (93.93%), while low-frequency, high-polysemy words achieved the lowest (81.14%). Our analysis quantitatively revealed that both frequency and polysemy contributed to accuracy improvement, but polysemy had a greater impact on accuracy than frequency.<\/jats:p>","DOI":"10.3390\/bdcc10030067","type":"journal-article","created":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T13:58:03Z","timestamp":1772114283000},"page":"67","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Validating the Effectiveness of Fine-Tuning for Semantic Classification of Japanese Katakana Words: An Analysis of Frequency and Polysemy Effects on Accuracy"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2504-2421","authenticated-orcid":false,"given":"Kazuki","family":"Kodaki","sequence":"first","affiliation":[{"name":"Department of Computer and Information Sciences, Faculty of Engineering, Ibaraki University, Ibaraki 316-8511, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8101-2796","authenticated-orcid":false,"given":"Minoru","family":"Sasaki","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Sciences, Faculty of Engineering, Ibaraki University, Ibaraki 316-8511, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1145\/1459352.1459355","article-title":"Word sense disambiguation: A survey","volume":"41","author":"Navigli","year":"2009","journal-title":"ACM Comput. Surv."},{"key":"ref_2","unstructured":"Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019, January 2\u20137). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Minneapolis, MN, USA."},{"key":"ref_3","unstructured":"Zhuang, L., Wayne, L., Ya, S., and Jun, Z. (2021, January 13\u201315). A robustly optimized BERT pre-training approach with post-training. Proceedings of the 20th Chinese National Conference on Computational Linguistics, Huhhot, China."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Maru, M., Conia, S., Bevilacqua, M., and Navigli, R. (2022, January 22\u201327). Nibbling at the hard core of word sense disambiguation. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Dublin, Ireland.","DOI":"10.18653\/v1\/2022.acl-long.324"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Blevins, T., and Zettlemoyer, L. (2020, January 5\u201310). Moving down the long tail of word sense disambiguation with gloss informed bi-encoders. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Online.","DOI":"10.18653\/v1\/2020.acl-main.95"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Masethe, H.D., Masethe, M.A., Ojo, S.O., Owolawi, P.A., and Giunchiglia, F. (2025). Hybrid transformer-based large language models for word sense disambiguation in the low-resource Sesotho sa Leboa language. Appl. Sci., 15.","DOI":"10.3390\/app15073608"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Mizuki, S., and Okazaki, N. (2023, January 2\u20136). Semantic specialization for knowledge-based word sense disambiguation. Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, Dubrovnik, Croatia.","DOI":"10.18653\/v1\/2023.eacl-main.251"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Wang, M., and Wang, Y. (2020, January 16\u201320). A synset relation-enhanced framework with a try-again mechanism for word sense disambiguation. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online.","DOI":"10.18653\/v1\/2020.emnlp-main.504"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"101861","DOI":"10.1016\/j.inffus.2023.101861","article-title":"ChatGPT: Jack of all trades, master of none","volume":"99","author":"Cichecki","year":"2023","journal-title":"Inf. Fusion"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Kang, H., Blevins, T., and Zettlemoyer, L. (2024, January 17\u201322). Translate to disambiguate: Zero-shot multilingual word sense disambiguation with pretrained language models. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, St. Julian\u2019s, Malta.","DOI":"10.18653\/v1\/2024.eacl-long.94"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Tran, V.-H., Dabre, R., Kaing, H., Song, H., Tanaka, H., and Utiyama, M. (2025, January 20). Exploiting word sense disambiguation in large language models for machine translation. Proceedings of the First Workshop on Language Models for Low-Resource Languages, Abu Dhabi, United Arab Emirates. Available online: https:\/\/aclanthology.org\/2025.loreslm-1.10\/.","DOI":"10.18653\/v1\/2025.loresmt-1.2"},{"key":"ref_12","unstructured":"LLM-jp Consortium (2026, January 18). LLM-jp: Japanese Large Language Models. Available online: https:\/\/llm-jp.nii.ac.jp\/."},{"key":"ref_13","unstructured":"Stability AI (2026, January 18). Japanese StableLM: Japanese Language Models. Available online: https:\/\/huggingface.co\/stabilityai\/japanese-stablelm-base-alpha-7b."},{"key":"ref_14","unstructured":"Fujii, K., Nakamura, T., Loem, M., Iida, H., Ohi, M., Hattori, K., Shota, H., Mizuki, S., Yokota, R., and Okazaki, N. (2024, January 7\u20139). Continual pre-training for cross-lingual LLM adaptation: Enhancing Japanese language capabilities. Proceedings of the First Conference on Language Modeling (COLM 2024), Philadelphia, PA, USA. Available online: https:\/\/openreview.net\/forum?id=TQdd1VhWbe."},{"key":"ref_15","unstructured":"Kyoto University NLP Group (2025, December 10). DeBERTa V3 Japanese Base Model. Available online: https:\/\/huggingface.co\/ku-nlp\/deberta-v3-base-japanese."},{"key":"ref_16","unstructured":"Jinnai, M. (2007). The Sociolinguistics of Loanwords: A Glocal Perspective on Japanese, Sekaishisosha-Kyogakusha."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Takamura, H., Nagata, R., and Kawasaki, Y. (2017, January 3\u20137). Analyzing semantic change in Japanese loanwords. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, Valencia, Spain.","DOI":"10.18653\/v1\/E17-1112"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"293","DOI":"10.5715\/jnlp.18.293","article-title":"On SemEval-2010 Japanese WSD task","volume":"18","author":"Okumura","year":"2011","journal-title":"J. Nat. Lang. Process."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Tan, Z., Li, D., Wang, S., Beigi, A., Jiang, B., Bhattacharjee, A., Karami, M., Li, J., Cheng, L., and Liu, H. (2024, January 12\u201316). Large language models for data annotation and synthesis: A survey. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Miami, FL, USA.","DOI":"10.18653\/v1\/2024.emnlp-main.54"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zhang, R., Li, Y., Ma, Y., Zhou, M., and Zou, L. (2023, January 6\u201310). LLMaAA: Making large language models as active annotators. Proceedings of the Association for Computational Linguistics: EMNLP 2023, Singapore.","DOI":"10.18653\/v1\/2023.findings-emnlp.872"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wu, T., Ding, X., Tang, M., Zhang, H., Qin, B., and Liu, T. (2023, January 9\u201314). NoisywikiHow: A benchmark for learning with real-world noisy labels in natural language processing. Proceedings of the Association for Computational Linguistics: ACL 2023, Toronto, ON, Canada.","DOI":"10.18653\/v1\/2023.findings-acl.299"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1007\/s10579-013-9261-0","article-title":"Balanced corpus of contemporary written Japanese","volume":"48","author":"Maekawa","year":"2014","journal-title":"Lang. Resour. Eval."},{"key":"ref_23","unstructured":"He, P., Liu, X., Gao, J., and Chen, W. (2021, January 3\u20137). DeBERTa: Decoding-enhanced BERT with disentangled attention. Proceedings of the 9th International Conference on Learning Representations (ICLR), Virtual."},{"key":"ref_24","unstructured":"Kudo, T., Yamamoto, K., and Matsumoto, Y. (2004, January 25\u201326). Applying conditional random fields to Japanese morphological analysis. Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, Barcelona, Spain."},{"key":"ref_25","unstructured":"Shogakukan Dictionary Editorial Department (Ed.) (2012). Digital Daijisen, Shogakukan. Available online: https:\/\/www.weblio.jp\/."},{"key":"ref_26","unstructured":"Zipf, G.K. (1949). Human Behavior and the Principle of Least Effort, Addison-Wesley."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","article-title":"A mathematical theory of communication","volume":"27","author":"Shannon","year":"1948","journal-title":"Bell Syst. Tech. J."},{"key":"ref_28","unstructured":"Bickel, P.J., Doksum, K., and Hodges, J.L. (1983). The notion of breakdown point. A Festschrift for Erich L. Lehmann, Wadsworth."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Efron, B., and Tibshirani, R.J. (1993). An Introduction to the Bootstrap, Chapman & Hall\/CRC.","DOI":"10.1007\/978-1-4899-4541-9"},{"key":"ref_30","unstructured":"Tohoku NLP Group (2026, January 18). BERT Japanese: Pretrained BERT Models for Japanese Text. Available online: https:\/\/github.com\/cl-tohoku\/bert-japanese."},{"key":"ref_31","unstructured":"Sumanathilaka, D.K., Micallef, N., and Hough, J. (2025, January 1). Prompt balance matters: Understanding how imbalanced few-shot learning affects multilingual sense disambiguation in LLMs. Proceedings of the Workshop on Beyond English: Natural Language Processing for All Languages in an Era of Large Language Models, Vienna, Austria. Available online: https:\/\/aclanthology.org\/2025.globalnlp-1.2."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Pasini, T., Raganato, A., and Navigli, R. (2021, January 2\u20139). XL-WSD: An extra-large and cross-lingual evaluation framework for word sense disambiguation. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual.","DOI":"10.1609\/aaai.v35i15.17609"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/j.artint.2012.07.001","article-title":"BabelNet: The automatic construction, evaluation and application of a wide-coverage multilingual semantic network","volume":"193","author":"Navigli","year":"2012","journal-title":"Artif. Intell."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1145\/219717.219748","article-title":"WordNet: A lexical database for English","volume":"38","author":"Miller","year":"1995","journal-title":"Commun. ACM"},{"key":"ref_35","unstructured":"Ganbat, N., Asada, S., and Komiya, K. (2024, January 28\u201330). Analysis of cross-linguality of XL-WSD dataset: A comparative study of Japanese and Dutch. Proceedings of the 38th Pacific Asia Conference on Language, Information and Computation, Bangkok, Thailand. Available online: https:\/\/aclanthology.org\/2024.paclic-1.32."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"72","DOI":"10.2307\/1412159","article-title":"The proof and measurement of association between two things","volume":"15","author":"Spearman","year":"1904","journal-title":"Am. J. Psychol."}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/10\/3\/67\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T14:33:05Z","timestamp":1772116385000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/10\/3\/67"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,26]]},"references-count":36,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["bdcc10030067"],"URL":"https:\/\/doi.org\/10.3390\/bdcc10030067","relation":{},"ISSN":["2504-2289"],"issn-type":[{"value":"2504-2289","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,26]]}}}