{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,15]],"date-time":"2025-03-15T05:10:19Z","timestamp":1742015419862,"version":"3.38.0"},"reference-count":92,"publisher":"Association for Natural Language Processing","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Journal of Natural Language Processing"],"published-print":{"date-parts":[[2025]]},"DOI":"10.5715\/jnlp.32.134","type":"journal-article","created":{"date-parts":[[2025,3,14]],"date-time":"2025-03-14T22:19:30Z","timestamp":1741990770000},"page":"134-175","source":"Crossref","is-referenced-by-count":0,"title":["Discovering Unusual Word Usages with Masked Language Model via Pseudo-label Training"],"prefix":"10.5715","volume":"32","author":[{"given":"Tatsuya","family":"Aoki","sequence":"first","affiliation":[{"name":"Institute of Science Tokyo"}]},{"given":"Jey","family":"Han Lau","sequence":"additional","affiliation":[{"name":"The University of Melbourne"}]},{"given":"Hidetaka","family":"Kamigaito","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology (NAIST)"}]},{"given":"Hiroya","family":"Takamura","sequence":"additional","affiliation":[{"name":"Institute of Science Tokyo"}]},{"given":"Timothy","family":"Baldwin","sequence":"additional","affiliation":[{"name":"The University of Melbourne"},{"name":"MBZUAI"}]},{"given":"Manabu","family":"Okumura","sequence":"additional","affiliation":[{"name":"Institute of Science Tokyo"}]}],"member":"3685","reference":[{"key":"1","unstructured":"Agarap, A. F. (2018). \u201cDeep Learning using Rectified Linear Units (ReLU).\u201d <i>CoRR<\/i>, abs\/1803.08375."},{"key":"2","doi-asserted-by":"crossref","unstructured":"Aoki, T., Sasano, R., Takamura, H., and Okumura, M. (2017). \u201cDistinguishing Japanese Non-standard Usages from Standard Ones.\u201d In <i>Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing<\/i>, pp. 2323\u20132328, Copenhagen, Denmark. Association for Computational Linguistics.","DOI":"10.18653\/v1\/D17-1246"},{"key":"3","doi-asserted-by":"crossref","unstructured":"Aoki, T., Sasano, R., Takamura, H., and Okumura, M. (2019). \u201cDetecting Non-standard Word Usages from Social Media.\u201d <i>Journal of Natural Language Processing<\/i>, 26 (2), pp. 381\u2013406.","DOI":"10.5715\/jnlp.26.381"},{"key":"4","doi-asserted-by":"crossref","unstructured":"Arora, K., Shuster, K., Sukhbaatar, S., and Weston, J. (2022). \u201cDirector: Generator-Classifiers For Supervised Language Modeling.\u201d In He, Y., Ji, H., Li, S., Liu, Y., and Chang, C.-H. (Eds.), <i>Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)<\/i>, pp. 512\u2013526, Online only. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2022.aacl-main.39"},{"key":"5","doi-asserted-by":"crossref","unstructured":"Aw, A., Zhang, M., Xiao, J., and Su, J. (2006). \u201cA Phrase-Based Statistical Model for SMS Text Normalization.\u201d In <i>Proceedings of the COLING\/ACL 2006 Main Conference Poster Sessions<\/i>, pp. 33\u201340, Sydney, Australia. Association for Computational Linguistics.","DOI":"10.3115\/1273073.1273078"},{"key":"6","unstructured":"Ba, J. L., Kiros, J. R., and Hinton, G. E. (2016). \u201cLayer Normalization.\u201d <i>CoRR<\/i>, abs\/1607.06450."},{"key":"7","doi-asserted-by":"crossref","unstructured":"Bamman, D., Dyer, C., and Smith, N. A. (2014). \u201cDistributed Representations of Geographically Situated Language.\u201d In <i>Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)<\/i>, pp. 828\u2013834, Baltimore, Maryland. Association for Computational Linguistics.","DOI":"10.3115\/v1\/P14-2134"},{"key":"8","doi-asserted-by":"crossref","unstructured":"Barteld, F. (2017). \u201cDetecting Spelling Variants in Non-Standard Texts.\u201d In <i>Proceedings of the Student Research Workshop at the 15th Conference of the European Chapter of the Association for Computational Linguistics<\/i>, pp. 11\u201322, Valencia, Spain. Association for Computational Linguistics.","DOI":"10.18653\/v1\/E17-4002"},{"key":"9","doi-asserted-by":"crossref","unstructured":"Bergsma, S., Lin, D., and Goebel, R. (2008). \u201cDiscriminative Learning of Selectional Preference from Unlabeled Text.\u201d In <i>Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing<\/i>, pp. 59\u201368, Honolulu, Hawaii. Association for Computational Linguistics.","DOI":"10.3115\/1613715.1613725"},{"key":"10","doi-asserted-by":"crossref","unstructured":"Bevilacqua, M., Pasini, T., Raganato, A., and Navigli, R. (2021). \u201cRecent Trends in Word Sense Disambiguation: A Survey.\u201d In Zhou, Z.-H. (Ed.), <i>Proceedings of the 30th International Joint Conference on Artificial Intelligence, IJCAI-21<\/i>, pp. 4330\u20134338. International Joint Conferences on Artificial Intelligence Organization. Survey Track.","DOI":"10.24963\/ijcai.2021\/593"},{"key":"11","doi-asserted-by":"crossref","unstructured":"Bird, S. (2006). \u201cNLTK: The Natural Language Toolkit.\u201d In <i>Proceedings of the COLING\/ACL 2006 Interactive Presentation Sessions<\/i>, pp. 69\u201372, Sydney, Australia. Association for Computational Linguistics.","DOI":"10.3115\/1225403.1225421"},{"key":"12","doi-asserted-by":"crossref","unstructured":"Bolding, Q., Liao, B., Denis, B., Luo, J., and Monz, C. (2023). \u201cAsk Language Model to Clean Your Noisy Translation Data.\u201d In Bouamor, H., Pino, J., and Bali, K. (Eds.), <i>Findings of the Association for Computational Linguistics: EMNLP 2023<\/i>, pp. 3215\u20133236, Singapore. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2023.findings-emnlp.212"},{"key":"13","unstructured":"Bsharat, S. M., Myrzakhan, A., and Shen, Z. (2024). \u201cPrincipled Instructions Are All You Need for Questioning LLaMA-1\/2, GPT-3.5\/4.\u201d <i>CoRR<\/i>, abs\/2312.16171."},{"key":"14","doi-asserted-by":"crossref","unstructured":"Cho, W. I. and Kim, S. (2021). \u201cGoogle-trickers, Yaminjeongeum, and Leetspeak: An Empirical Taxonomy for Intentionally Noisy User-Generated Text.\u201d In Xu, W., Ritter, A., Baldwin, T., and Rahimi, A. (Eds.), <i>Proceedings of the 7th Workshop on Noisy User-generated Text (W-NUT 2021)<\/i>, pp. 56\u201361, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2021.wnut-1.7"},{"key":"15","doi-asserted-by":"crossref","unstructured":"Choi, M., Lee, S., Choi, E., Park, H., Lee, J., Lee, D., and Lee, J. (2021). \u201cMelBERT: Metaphor Detection via Contextualized Late Interaction using Metaphorical Identification Theories.\u201d In Toutanova, K., Rumshisky, A., Zettlemoyer, L., Hakkani-Tur, D., Beltagy, I., Bethard, S., Cotterell, R., Chakraborty, T., and Zhou, Y. (Eds.), <i>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies<\/i>, pp. 1763\u20131773, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2021.naacl-main.141"},{"key":"16","unstructured":"Cook, P., Lau, J. H., McCarthy, D., and Baldwin, T. (2014). \u201cNovel Word-sense Identification.\u201d In <i>Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers<\/i>, pp. 1624\u20131635, Dublin, Ireland. Dublin City University and Association for Computational Linguistics."},{"key":"17","doi-asserted-by":"crossref","unstructured":"Crisp, P., Gibbs, R., Deignan, A., Low, G., Steen, G., Cameron, L., Semino, E., Grady, J., Cienki, A., K^^c3^^b6vecses, Z., and Group, T. (2007). \u201cMIP: A Method for Identifying Metaphorically used Words in Discourse.\u201d <i>Metaphor and Symbol<\/i>, 22, pp. 1\u201339.","DOI":"10.1080\/10926480709336752"},{"key":"18","unstructured":"Del Tredici, M. and Fern\u00e1ndez, R. (2018). \u201cThe Road to Success: Assessing the Fate of Linguistic Innovations in Online Communities.\u201d In <i>Proceedings of the 27th International Conference on Computational Linguistics<\/i>, pp. 1591\u20131603, Santa Fe, New Mexico, USA. Association for Computational Linguistics."},{"key":"19","unstructured":"Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019). \u201cBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.\u201d In <i>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)<\/i>, pp. 4171\u20134186, Minneapolis, Minnesota. Association for Computational Linguistics."},{"key":"20","unstructured":"Eisenstein, J. (2013). \u201cWhat to Do about Bad Language on the Internet.\u201d In <i>Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies<\/i>, pp. 359\u2013369, Atlanta, Georgia. Association for Computational Linguistics."},{"key":"21","doi-asserted-by":"crossref","unstructured":"Elhoushi, M., Shrivastava, A., Liskovich, D., Hosmer, B., Wasti, B., Lai, L., Mahmoud, A., Acun, B., Agarwal, S., Roman, A., Aly, A., Chen, B., and Wu, C.-J. (2024). \u201cLayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding.\u201d In Ku, L.-W., Martins, A., and Srikumar, V. (Eds.), <i>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)<\/i>, pp. 12622\u201312642, Bangkok, Thailand. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2024.acl-long.681"},{"key":"22","doi-asserted-by":"crossref","unstructured":"Erk, K. (2006). \u201cUnknown Word Sense Detection as Outlier Detection.\u201d In <i>Proceedings of the Human Language Technology Conference of the NAACL, Main Conference<\/i>, pp. 128\u2013135, New York City, USA. Association for Computational Linguistics.","DOI":"10.3115\/1220835.1220852"},{"key":"23","unstructured":"Ferraresi, A., Zanchetta, E., Baroni, M., and Bernardini, S. (2008). \u201cIntroducing and Evaluating ukWaC, a Very Large Web-derived Corpus of English.\u201d In <i>Proceedings of the 4th Web as Corpus Workshop (WAC-4)<\/i>."},{"key":"24","doi-asserted-by":"crossref","unstructured":"Fillies, J. and Paschke, A. (2024). \u201cSimple LLM based Approach to Counter Algospeak.\u201d In Chung, Y.-L., Talat, Z., Nozza, D., Plaza-del Arco, F. M., R\u00f6ttger, P., Mostafazadeh Davani, A., and Calabrese, A. (Eds.), <i>Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024)<\/i>, pp. 136\u2013145, Mexico City, Mexico. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2024.woah-1.10"},{"key":"25","doi-asserted-by":"crossref","unstructured":"Fleiss, J. et al. (1971). \u201cMeasuring Nominal Scale Agreement among Many Raters.\u201d <i>Psychological Bulletin<\/i>, 76 (5), pp. 378\u2013382.","DOI":"10.1037\/h0031619"},{"key":"26","unstructured":"Fujii, K., Nakamura, T., Loem, M., Iida, H., Ohi, M., Hattori, K., Shota, H., Mizuki, S., Yokota, R., and Okazaki, N. (2024). \u201cContinual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilities.\u201d <i>CoRR<\/i>, abs\/2404.17790."},{"key":"27","doi-asserted-by":"crossref","unstructured":"Gao, J., Yu, C., Wang, W., Zhao, H., and Xu, R. (2022). \u201cMask-then-Fill: A Flexible and Effective Data Augmentation Framework for Event Extraction.\u201d In Goldberg, Y., Kozareva, Z., and Zhang, Y. (Eds.), <i>Findings of the Association for Computational Linguistics: EMNLP 2022<\/i>, pp. 4537\u20134544, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2022.findings-emnlp.332"},{"key":"28","doi-asserted-by":"crossref","unstructured":"Gera, A., Friedman, R., Arviv, O., Gunasekara, C., Sznajder, B., Slonim, N., and Shnarch, E. (2023). \u201cThe Benefits of Bad Advice: Autocontrastive Decoding across Model Layers.\u201d In Rogers, A., Boyd-Graber, J., and Okazaki, N. (Eds.), <i>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)<\/i>, pp. 10406\u201310420, Toronto, Canada. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2023.acl-long.580"},{"key":"29","doi-asserted-by":"crossref","unstructured":"Giulianelli, M., Del Tredici, M., and Fern\u00e1ndez, R. (2020). \u201cAnalysing Lexical Semantic Change with Contextualised Word Representations.\u201d In <i>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics<\/i>, pp. 3960\u20133973, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2020.acl-main.365"},{"key":"30","doi-asserted-by":"crossref","unstructured":"Hamilton, W. L., Clark, K., Leskovec, J., and Jurafsky, D. (2016a). \u201cInducing Domain-Specific Sentiment Lexicons from Unlabeled Corpora.\u201d In <i>Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing<\/i>, pp. 595\u2013605, Austin, Texas. Association for Computational Linguistics.","DOI":"10.18653\/v1\/D16-1057"},{"key":"31","doi-asserted-by":"crossref","unstructured":"Hamilton, W. L., Leskovec, J., and Jurafsky, D. (2016b). \u201cDiachronic Word Embeddings Reveal Statistical Laws of Semantic Change.\u201d In <i>Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)<\/i>, pp. 1489\u20131501, Berlin, Germany. Association for Computational Linguistics.","DOI":"10.18653\/v1\/P16-1141"},{"key":"32","unstructured":"Han, B. and Baldwin, T. (2011). \u201cLexical Normalisation of Short Text Messages: Makn Sens a #twitter.\u201d In <i>Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies<\/i>, pp. 368\u2013378, Portland, Oregon, USA. Association for Computational Linguistics."},{"key":"33","doi-asserted-by":"crossref","unstructured":"Han, B., Cook, P., and Baldwin, T. (2013). \u201cLexical Normalization for Social Media Text.\u201d <i>ACM Transactions on Intelligent Systems and Technology<\/i>, 4, pp. 1\u201327.","DOI":"10.1145\/2414425.2414430"},{"key":"34","doi-asserted-by":"crossref","unstructured":"Heinzerling, B. and Inui, K. (2021). \u201cLanguage Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries.\u201d In Merlo, P., Tiedemann, J., and Tsarfaty, R. (Eds.), <i>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume<\/i>, pp. 1772\u20131791, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2021.eacl-main.153"},{"key":"35","unstructured":"Hendrycks, D. and Gimpel, K. (2016). \u201cBridging Nonlinearities and Stochastic Regularizers with Gaussian Error Linear Units.\u201d <i>CoRR<\/i>, abs\/1606.08415."},{"key":"36","doi-asserted-by":"crossref","unstructured":"Hu, R., Li, S., and Liang, S. (2019). \u201cDiachronic Sense Modeling with Deep Contextualized Word Embeddings: An Ecological View.\u201d In <i>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics<\/i>, pp. 3899\u20133908, Florence, Italy. Association for Computational Linguistics.","DOI":"10.18653\/v1\/P19-1379"},{"key":"37","unstructured":"Huang, H., Wen, Z., Yu, D., Ji, H., Sun, Y., Han, J., and Li, H. (2013). \u201cResolving Entity Morphs in Censored Data.\u201d In <i>Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)<\/i>, pp. 1083\u20131093, Sofia, Bulgaria. Association for Computational Linguistics."},{"key":"38","doi-asserted-by":"crossref","unstructured":"Inoue, S., Komachi, M., Ogiso, T., Takamura, H., and Mochihashi, D. (2022). \u201cInfinite SCAN: An Infinite Model of Diachronic Semantic Change.\u201d In Goldberg, Y., Kozareva, Z., and Zhang, Y. (Eds.), <i>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing<\/i>, pp. 1605\u20131616, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2022.emnlp-main.104"},{"key":"39","doi-asserted-by":"crossref","unstructured":"Kaneko, M., Mita, M., Kiyono, S., Suzuki, J., and Inui, K. (2020). \u201cEncoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction.\u201d In <i>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics<\/i>, pp. 4248\u20134254, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2020.acl-main.391"},{"key":"40","unstructured":"Kingma, D. P. and Ba, J. (2014). \u201cAdam: A Method for Stochastic Optimization.\u201d <i>CoRR<\/i>, abs\/1412.6980."},{"key":"41","doi-asserted-by":"crossref","unstructured":"Kiyono, S., Suzuki, J., Mita, M., Mizumoto, T., and Inui, K. (2019). \u201cAn Empirical Study of Incorporating Pseudo Data into Grammatical Error Correction.\u201d In <i>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)<\/i>, pp. 1236\u20131242, Hong Kong, China. Association for Computational Linguistics.","DOI":"10.18653\/v1\/D19-1119"},{"key":"42","unstructured":"Kudo, T., Yamamoto, K., and Matsumoto, Y. (2004). \u201cApplying Conditional Random Fields to Japanese Morphological Analysis.\u201d In <i>Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing<\/i>, pp. 230\u2013237, Barcelona, Spain. Association for Computational Linguistics."},{"key":"43","doi-asserted-by":"crossref","unstructured":"Kulkarni, V., Al-Rfou, R., Perozzi, B., and Skiena, S. (2015). \u201cStatistically Significant Detection of Linguistic Change.\u201d In <i>Proceedings of The Web Conference<\/i>, pp. 625\u2013635.","DOI":"10.1145\/2736277.2741627"},{"key":"44","doi-asserted-by":"crossref","unstructured":"Kulkarni, V. and Wang, W. Y. (2018). \u201cSimple Models for Word Formation in Slang.\u201d In <i>Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)<\/i>, pp. 1424\u20131434, New Orleans, Louisiana. Association for Computational Linguistics.","DOI":"10.18653\/v1\/N18-1129"},{"key":"45","unstructured":"Kutuzov, A., \u00d8vrelid, L., Szymanski, T., and Velldal, E. (2018). \u201cDiachronic Word Embeddings and Semantic Shifts: A Survey.\u201d In <i>Proceedings of the 27th International Conference on Computational Linguistics<\/i>, pp. 1384\u20131397, Santa Fe, New Mexico, USA. Association for Computational Linguistics."},{"key":"46","doi-asserted-by":"crossref","unstructured":"Landis, J. and Koch, G. (1977). \u201cThe Measurement of Observer Agreement for Categorical Data.\u201d <i>Biometrics<\/i>, 33 (1), pp. 159\u2013174.","DOI":"10.2307\/2529310"},{"key":"47","unstructured":"Lau, J. H., Cook, P., McCarthy, D., Newman, D., and Baldwin, T. (2012). \u201cWord Sense Induction for Novel Sense Detection.\u201d In <i>Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics<\/i>, pp. 591\u2013601, Avignon, France. Association for Computational Linguistics."},{"key":"48","unstructured":"Li, C. and Liu, Y. (2015). \u201cJoint POS Tagging and Text Normalization for Informal Text.\u201d In <i>Proceedings of IJCAI<\/i>, pp. 1263\u20131269."},{"key":"49","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, S., Lin, C., and Guerin, F. (2023a). \u201cMetaphor Detection via Explicit Basic Meanings Modelling.\u201d In Rogers, A., Boyd-Graber, J., and Okazaki, N. (Eds.), <i>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)<\/i>, pp. 91\u2013100, Toronto, Canada. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2023.acl-short.9"},{"key":"50","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, S., Lin, C., Guerin, F., and Barrault, L. (2023b). \u201cFrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning.\u201d In Vlachos, A. and Augenstein, I. (Eds.), <i>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics<\/i>, pp. 1558\u20131563, Dubrovnik, Croatia. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2023.eacl-main.114"},{"key":"51","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., and Stoyanov, V. (2019). \u201cRoBERTa: A Robustly Optimized BERT Pretraining Approach.\u201d <i>CoRR<\/i>, abs\/1907.11692."},{"key":"52","doi-asserted-by":"crossref","unstructured":"Lourentzou, I., Manghnani, K., and Zhai, C. (2019). \u201cAdapting Sequence to Sequence Models for Text Normalization in Social Media.\u201d <i>Proceedings of the ICWSM<\/i>, 13 (01), pp. 335\u2013345.","DOI":"10.1609\/icwsm.v13i01.3234"},{"key":"53","doi-asserted-by":"crossref","unstructured":"Lucy, L. and Bamman, D. (2021). \u201cCharacterizing English Variation across Social Media Communities with BERT.\u201d <i>Transactions of the Association for Computational Linguistics<\/i>, 9, pp. 538\u2013556.","DOI":"10.1162\/tacl_a_00383"},{"key":"54","unstructured":"Maekawa, K., Yamazaki, M., Maruyama, T., Yamaguchi, M., Ogura, H., Kashino, W., Ogiso, T., Koiso, H., and Den, Y. (2010). \u201cDesign, Compilation, and Preliminary Analyses of Balanced Corpus of Contemporary Written Japanese.\u201d In <i>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC\u201910)<\/i>, pp. 1483\u20131486, Valletta, Malta. European Language Resources Association (ELRA)."},{"key":"55","unstructured":"Martinc, M., Kralj Novak, P., and Pollak, S. (2020). \u201cLeveraging Contextual Embeddings for Detecting Diachronic Semantic Shift.\u201d In <i>Proceedings of the 12th Language Resources and Evaluation Conference<\/i>, pp. 4811\u20134819, Marseille, France. European Language Resources Association."},{"key":"56","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., and Dean, J. (2013). \u201cDistributed Representations of Words and Phrases and their Compositionality.\u201d In <i>Advances in Neural Information Processing Systems 26<\/i>, pp. 3111\u20133119."},{"key":"57","doi-asserted-by":"crossref","unstructured":"Montariol, S., Martinc, M., and Pivovarova, L. (2021). \u201cScalable and Interpretable Semantic Change Detection.\u201d In Toutanova, K., Rumshisky, A., Zettlemoyer, L., Hakkani-Tur, D., Beltagy, I., Bethard, S., Cotterell, R., Chakraborty, T., and Zhou, Y. (Eds.), <i>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies<\/i>, pp. 4642\u20134652, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2021.naacl-main.369"},{"key":"58","doi-asserted-by":"crossref","unstructured":"Nagata, R., Takamura, H., Otani, N., and Kawasaki, Y. (2023). \u201cVariance Matters: Detecting Semantic Differences without Corpus\/Word Alignment.\u201d In Bouamor, H., Pino, J., and Bali, K. (Eds.), <i>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing<\/i>, pp. 15609\u201315622, Singapore. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2023.emnlp-main.965"},{"key":"59","doi-asserted-by":"crossref","unstructured":"Navigli, R. (2009). \u201cWord Sense Disambiguation: A Survey.\u201d <i>ACM Computing Surveys<\/i>, 41 (2), pp. 1\u201369.","DOI":"10.1145\/1459352.1459355"},{"key":"60","doi-asserted-by":"crossref","unstructured":"Ng, H. T., Wu, S. M., Briscoe, T., Hadiwinoto, C., Susanto, R. H., and Bryant, C. (2014). \u201cThe CoNLL-2014 Shared Task on Grammatical Error Correction.\u201d In <i>Proceedings of the 18th Conference on Computational Natural Language Learning: Shared Task<\/i>, pp. 1\u201314, Baltimore, Maryland. Association for Computational Linguistics.","DOI":"10.3115\/v1\/W14-1701"},{"key":"61","unstructured":"OpenAI (2023). \u201cIntroducing ChatGPT.\u201d https:\/\/openai.com\/blog\/chatgpt."},{"key":"62","unstructured":"OpenAI (2024). \u201cGPT-4 Technical Report.\u201d <i>CoRR<\/i>, abs\/2303.08774."},{"key":"63","unstructured":"Park, S., Moon, J., Kim, S., Cho, W. I., Han, J. Y., Park, J., Song, C., Kim, J., Song, Y., Oh, T., Lee, J., Oh, J., Lyu, S., Jeong, Y., Lee, I., Seo, S., Lee, D., Kim, H., Lee, M., Jang, S., Do, S., Kim, S., Lim, K., Lee, J., Park, K., Shin, J., Kim, S., Park, L., Park, L., Oh, A., Ha (NAVER AI Lab), J.-W., Cho, K., and Cho, K. (2021). \u201cKLUE: Korean Language Understanding Evaluation.\u201d In Vanschoren, J. and Yeung, S. (Eds.), <i>Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks<\/i>, Vol. 1."},{"key":"64","unstructured":"Pauls, A. and Klein, D. (2012). \u201cLarge-Scale Syntactic Language Modeling with Treelets.\u201d In <i>Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)<\/i>, pp. 959\u2013968, Jeju Island, Korea. Association for Computational Linguistics."},{"key":"65","doi-asserted-by":"crossref","unstructured":"Pei, Z., Sun, Z., and Xu, Y. (2019). \u201cSlang Detection and Identification.\u201d In <i>Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)<\/i>, pp. 881\u2013889, Hong Kong, China. Association for Computational Linguistics.","DOI":"10.18653\/v1\/K19-1082"},{"key":"66","doi-asserted-by":"crossref","unstructured":"Petroni, F., Rockt\u00e4schel, T., Riedel, S., Lewis, P., Bakhtin, A., Wu, Y., and Miller, A. (2019). \u201cLanguage Models as Knowledge Bases?\u201d In <i>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)<\/i>, pp. 2463\u20132473, Hong Kong, China. Association for Computational Linguistics.","DOI":"10.18653\/v1\/D19-1250"},{"key":"67","doi-asserted-by":"crossref","unstructured":"Poon, H., Cherry, C., and Toutanova, K. (2009). \u201cUnsupervised Morphological Segmentation with Log-Linear Models.\u201d In <i>Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics<\/i>, pp. 209\u2013217, Boulder, Colorado. Association for Computational Linguistics.","DOI":"10.3115\/1620754.1620785"},{"key":"68","unstructured":"Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., and Liu, P. J. (2020). \u201cExploring the Limits of Transfer Learning with a Unified Text-to-text Transformer.\u201d <i>Journal of Machine Learning Research<\/i>, 21 (1), pp. 5485\u20135551."},{"key":"69","doi-asserted-by":"crossref","unstructured":"Ruder, S. and Plank, B. (2018). \u201cStrong Baselines for Neural Semi-Supervised Learning under Domain Shift.\u201d In <i>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)<\/i>, pp. 1044\u20131054, Melbourne, Australia. Association for Computational Linguistics.","DOI":"10.18653\/v1\/P18-1096"},{"key":"70","unstructured":"Saito, I., Sadamitsu, K., Asano, H., and Matsuo, Y. (2014). \u201cMorphological Analysis for Japanese Noisy Text based on Character-level and Word-level Normalization.\u201d In <i>Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers<\/i>, pp. 1773\u20131782, Dublin, Ireland. Dublin City University and Association for Computational Linguistics."},{"key":"71","unstructured":"Saito, I., Suzuki, J., Nishida, K., Sadamitsu, K., Kobashikawa, S., Masumura, R., Matsumoto, Y., and Tomita, J. (2017). \u201cImproving Neural Text Normalization with Data Augmentation at Character- and Morphological Levels.\u201d In <i>Proceedings of the 8th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)<\/i>, pp. 257\u2013262, Taipei, Taiwan. Asian Federation of Natural Language Processing."},{"key":"72","unstructured":"Sboev, A. (2016). \u201cThe Sources of New Words and Expressions in the Chinese Internet Language and the Ways by which They Enter the Internet language.\u201d In <i>Proceedings of the 30th Pacific Asia Conference on Language, Information and Computation: Posters<\/i>, pp. 355\u2013361, Seoul, South Korea."},{"key":"73","doi-asserted-by":"crossref","unstructured":"Schmid, H. (1999). \u201cImprovements in Part-of-Speech Tagging with an Application to German.\u201d In <i>Natural Language Processing Using Very Large Corpora<\/i>, Vol. 11 of <i>Text, Speech and Language Processing<\/i>, pp. 13\u201326.","DOI":"10.1007\/978-94-017-2390-9_2"},{"key":"74","doi-asserted-by":"crossref","unstructured":"Sommerauer, P. and Fokkens, A. (2019). \u201cConceptual Change and Distributional Semantic Models: an Exploratory Study on Pitfalls and Possibilities.\u201d In <i>Proceedings of the 1st International Workshop on Computational Approaches to Historical Language Change<\/i>, pp. 223\u2013233, Florence, Italy. Association for Computational Linguistics.","DOI":"10.18653\/v1\/W19-4728"},{"key":"75","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R. (2014). \u201cDropout: A Simple Way to Prevent Neural Networks from Overfitting.\u201d <i>Journal of Machine Learning Research<\/i>, 15 (56), pp. 1929\u20131958."},{"key":"76","doi-asserted-by":"crossref","unstructured":"Steen, E., Yurechko, K., and Klug, D. (2023). \u201cYou Can (Not) Say What You Want: Using Algospeak to Contest and Evade Algorithmic Content Moderation on TikTok.\u201d <i>Social Media + Society<\/i>, 9 (3), 20563051231194586.","DOI":"10.1177\/20563051231194586"},{"key":"77","doi-asserted-by":"crossref","unstructured":"Stewart, I. and Eisenstein, J. (2018). \u201cMaking \u201cfetch\u201d Happen: The Influence of Social and Linguistic Context on Nonstandard Word Growth and Decline.\u201d In <i>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing<\/i>, pp. 4360\u20134370, Brussels, Belgium. Association for Computational Linguistics.","DOI":"10.18653\/v1\/D18-1467"},{"key":"78","doi-asserted-by":"crossref","unstructured":"Sun, Z., Hu, Q., Gupta, R., Zemel, R., and Xu, Y. (2024). \u201cToward Informal Language Processing: Knowledge of Slang in Large Language Models.\u201d In Duh, K., Gomez, H., and Bethard, S. (Eds.), <i>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)<\/i>, pp. 1683\u20131701, Mexico City, Mexico. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2024.naacl-long.94"},{"key":"79","doi-asserted-by":"crossref","unstructured":"Sun, Z., Zemel, R., and Xu, Y. (2022). \u201cSemantically Informed Slang Interpretation.\u201d In Carpuat, M., de Marneffe, M.-C., and Meza Ruiz, I. V. (Eds.), <i>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies<\/i>, pp. 5213\u20135231, Seattle, United States. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2022.naacl-main.383"},{"key":"80","doi-asserted-by":"crossref","unstructured":"Tarumoto, S., Hatagaki, K., Miyata, R., Kajiwara, T., and Ninomiya, T. (2024). Evaluating ChatGPT\u2019s Ability to Generate Japanese. <i>Journal of Natural Language Processing<\/i>, 31 (2), pp. 349\u2013373.","DOI":"10.5715\/jnlp.31.349"},{"key":"81","doi-asserted-by":"crossref","unstructured":"Tolmachev, A., Kawahara, D., and Kurohashi, S. (2018). \u201cJuman++: A Morphological Analysis Toolkit for Scriptio Continua.\u201d In <i>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations<\/i>, pp. 54\u201359, Brussels, Belgium. Association for Computational Linguistics.","DOI":"10.18653\/v1\/D18-2010"},{"key":"82","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, \u023d., and Polosukhin, I. (2017). \u201cAttention is All you Need.\u201d In <i>Advances in Neural Information Processing Systems 30<\/i>, pp. 5998\u20136008."},{"key":"83","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., and Bowman, S. R. (2019). \u201cGLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding.\u201d In <i>International Conference on Learning Representations<\/i>.","DOI":"10.18653\/v1\/W18-5446"},{"key":"84","doi-asserted-by":"crossref","unstructured":"Wilks, Y. (1975). \u201cA Preferential, Pattern-seeking, Semantics for Natural Language Inference.\u201d <i>Artificial Intelligence<\/i>, 6 (1), pp. 53\u201374.","DOI":"10.1016\/0004-3702(75)90016-8"},{"key":"85","doi-asserted-by":"crossref","unstructured":"Wilks, Y. (1978). \u201cMaking Preferences More Active.\u201d <i>Artificial Intelligence<\/i>, 11 (3), pp. 197\u2013223.","DOI":"10.1016\/0004-3702(78)90001-2"},{"key":"86","doi-asserted-by":"crossref","unstructured":"Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., Davison, J., Shleifer, S., von Platen, P., Ma, C., Jernite, Y., Plu, J., Xu, C., Scao, T. L., Gugger, S., Drame, M., Lhoest, Q., and Rush, A. M. (2020). \u201cHuggingFace\u2019s Transformers: State-of-the-art Natural Language Processing.\u201d <i>CoRR<\/i>, abs\/1910.03771.","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"87","doi-asserted-by":"crossref","unstructured":"Xu, H., Shu, L., Yu, P., and Liu, B. (2020). \u201cUnderstanding Pre-trained BERT for Aspect-based Sentiment Analysis.\u201d In <i>Proceedings of the 28th International Conference on Computational Linguistics<\/i>, pp. 244\u2013250, Barcelona, Spain (Online). International Committee on Computational Linguistics.","DOI":"10.18653\/v1\/2020.coling-main.21"},{"key":"88","doi-asserted-by":"crossref","unstructured":"Yan, M., Lin, Y.-R., Hwa, R., Mert Ertugrul, A., Guo, M., and Chung, W.-T. (2020). \u201cMimicProp: Learning to Incorporate Lexicon Knowledge into Distributed Word Representation for Social Media Analysis.\u201d <i>Proceedings of ICWSM<\/i>, 14 (1), pp. 738\u2013749.","DOI":"10.1609\/icwsm.v14i1.7339"},{"key":"89","doi-asserted-by":"crossref","unstructured":"Yang, Y. and Eisenstein, J. (2017). \u201cOvercoming Language Variation in Sentiment Analysis with Social Attention.\u201d <i>Transactions of the Association for Computational Linguistics<\/i>, 5, pp. 295\u2013307.","DOI":"10.1162\/tacl_a_00062"},{"key":"90","doi-asserted-by":"crossref","unstructured":"Zhang, B., Huang, H., Pan, X., Li, S., Lin, C.-Y., Ji, H., Knight, K., Wen, Z., Sun, Y., Han, J., and Yener, B. (2015). \u201cContext-aware Entity Morph Decoding.\u201d In <i>Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)<\/i>, pp. 586\u2013595, Beijing, China. Association for Computational Linguistics.","DOI":"10.3115\/v1\/P15-1057"},{"key":"91","doi-asserted-by":"crossref","unstructured":"Zhou, W., Ge, T., Xu, K., Wei, F., and Zhou, M. (2019). \u201cBERT-based Lexical Substitution.\u201d In <i>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics<\/i>, pp. 3368\u20133373, Florence, Italy. Association for Computational Linguistics.","DOI":"10.18653\/v1\/P19-1328"},{"key":"92","doi-asserted-by":"crossref","unstructured":"Zhu, W. and Bhat, S. (2021). \u201cEuphemistic Phrase Detection by Masked Language Model.\u201d In Moens, M.-F., Huang, X., Specia, L., and Yih, S. W.-t. (Eds.), <i>Findings of the Association for Computational Linguistics: EMNLP 2021<\/i>, pp. 163\u2013168, Punta Cana, Dominican Republic. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2021.findings-emnlp.16"}],"container-title":["Journal of Natural Language Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/jnlp\/32\/1\/32_134\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,15]],"date-time":"2025-03-15T04:37:04Z","timestamp":1742013424000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/jnlp\/32\/1\/32_134\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":92,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.5715\/jnlp.32.134","relation":{},"ISSN":["1340-7619","2185-8314"],"issn-type":[{"value":"1340-7619","type":"print"},{"value":"2185-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}