{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T04:30:32Z","timestamp":1750480232261},"reference-count":45,"publisher":"Association for Natural Language Processing","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Journal of Natural Language Processing"],"published-print":{"date-parts":[[2024]]},"DOI":"10.5715\/jnlp.31.433","type":"journal-article","created":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T22:13:39Z","timestamp":1718403219000},"page":"433-455","source":"Crossref","is-referenced-by-count":2,"title":["Second Language Acquisition of Neural Language Models","\u8a00\u8a9e\u30e2\u30c7\u30eb\u306e\u7b2c\u4e8c\u8a00\u8a9e\u7372\u5f97"],"prefix":"10.5715","volume":"31","author":[{"given":"Miyu","family":"Oba","sequence":"first","affiliation":[{"name":"Nara Institute of Science and Technology (NAIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuki","family":"Kuribayashi","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroki","family":"Ouchi","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology (NAIST)"},{"name":"RIKEN"},{"name":"NINJAL"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taro","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology (NAIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"3685","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"Blevins, T., Gonen, H., and Zettlemoyer, L. (2022). \u201cAnalyzing the Mono- and Cross-Lingual Pretraining Dynamics of Multilingual Language Models.\u201d In <i>Proceedings of EMNLP<\/i>, pp. 3575\u20133590, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2022.emnlp-main.234"},{"key":"2","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D., Wu, J., Winter, C., Hesse, C., Chen, M., Sigler, E., Litwin, M., Gray, S., Chess, B., Clark, J., Berner, C., McCandlish, S., Radford, A., Sutskever, I., and Amodei, D. (2020). \u201cLanguage Models are Few-Shot Learners.\u201d In Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., and Lin, H. (Eds.), <i>Advances in Neural Information Processing Systems<\/i>, Vol. 33, pp. 1877\u20131901. Curran Associates, Inc."},{"key":"3","doi-asserted-by":"crossref","unstructured":"Bybee, J. L. (2013). \u201c49 Usage-based Theory and Exemplar Representations of Constructions.\u201d In <i>The Oxford Handbook of Construction Grammar<\/i>. Oxford University Press.","DOI":"10.1093\/oxfordhb\/9780195396683.013.0004"},{"key":"4","doi-asserted-by":"crossref","unstructured":"Chiswick, B. and Miller, P. (2004). \u201cLinguistic Distance: A Quantitative Measure of the Distance Between English and Other Languages.\u201d Tech. rep. 1246, Institute of Labor Economics (IZA).","DOI":"10.2139\/ssrn.575090"},{"key":"5","doi-asserted-by":"crossref","unstructured":"Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzm\u00e1n, F., Grave, E., Ott, M., Zettlemoyer, L., and Stoyanov, V. (2020). \u201cUnsupervised Cross-lingual Representation Learning at Scale.\u201d In <i>Proceedings of ACL<\/i>, pp. 8440\u20138451, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"6","unstructured":"Conneau, A. and Lample, G. (2019). \u201cCross-lingual Language Model Pretraining.\u201d In Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E., and Garnett, R. (Eds.), <i>Advances in Neural Information Processing Systems<\/i>, Vol. 32. Curran Associates, Inc."},{"key":"7","doi-asserted-by":"crossref","unstructured":"Cook, V. J. (1985). \u201cChomsky\u2019s Universal Grammar and Second Language Learning.\u201d <i>Applied Linguistics<\/i>, 6 (1), pp. 2\u201318.","DOI":"10.1093\/applin\/6.1.2"},{"key":"8","doi-asserted-by":"crossref","unstructured":"Deshpande, A., Talukdar, P., and Narasimhan, K. (2022). \u201cWhen is BERT Multilingual? Isolating Crucial Ingredients for Cross-lingual Transfer.\u201d In <i>Proceedings of NAACL<\/i>, pp. 3610\u20133623, Seattle, United States. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2022.naacl-main.264"},{"key":"9","doi-asserted-by":"crossref","unstructured":"Dong, D., Wu, H., He, W., Yu, D., and Wang, H. (2015). \u201cMulti-Task Learning for Multiple Language Translation.\u201d In <i>Proceedings of ACL<\/i>, pp. 1723\u20131732, Beijing, China. Association for Computational Linguistics.","DOI":"10.3115\/v1\/P15-1166"},{"key":"10","doi-asserted-by":"crossref","unstructured":"Ellis, R. (2010). \u201cSecond Language Acquisition, Teacher Education and Language Pedagogy.\u201d <i>Language Teaching<\/i>, 43 (2), pp. 182\u2013201.","DOI":"10.1017\/S0261444809990139"},{"key":"11","doi-asserted-by":"crossref","unstructured":"French, R. M. (1999). \u201cCatastrophic Forgetting in Connectionist Networks.\u201d <i>Trends in Cognitive Sciences<\/i>, 3 (4), pp. 128\u2013135.","DOI":"10.1016\/S1364-6613(99)01294-2"},{"key":"12","unstructured":"Grimes, B. F. and Grimes, J. (2002). \u201cEthnologue: Languages of the World. 14th Edition.\u201d <i>Dallas, TX: SIL International<\/i>."},{"key":"13","doi-asserted-by":"crossref","unstructured":"Haman, E., Wodniecka, Z., Marecka, M., Szewczyk, J., Bia\u019aecka-Pikul, M., Otwinowska, A., Mieszkowska, K., \u023duniewska, M., Ko\u019aak, J., Mi\u0119kisz, A., Kacprzak, A., Banasik, N., and Fory\u015b-Nogala, M. (2017). \u201cHow Does L1 and L2 Exposure Impact L1 Performance in Bilingual Children? Evidence from Polish-English Migrants to the United Kingdom.\u201d <i>Frontiers in Psychology<\/i>, 8. 1444.","DOI":"10.3389\/fpsyg.2017.01444"},{"key":"14","unstructured":"Hatch, E. M. (1983). <i>Psycholinguistics: A Second Language Perspective.<\/i> ERIC."},{"key":"15","unstructured":"Kecskes, I. (2008). \u201cThe Effect of The Second Language on the First Language.\u201d <i>Babylonia<\/i>, 2 (2), pp. 31\u201334."},{"key":"16","doi-asserted-by":"crossref","unstructured":"Kirov, C. and Cotterell, R. (2018). \u201cRecurrent Neural Networks in Linguistic Theory: Revisiting Pinker and Prince (1988) and the Past Tense Debate.\u201d <i>Transactions of the Association for Computational Linguistics<\/i>, 6, pp. 651\u2013665.","DOI":"10.1162\/tacl_a_00247"},{"key":"17","doi-asserted-by":"crossref","unstructured":"Koehn, P., Hoang, H., Birch, A., Callison-Burch, C., Federico, M., Bertoldi, N., Cowan, B., Shen, W., Moran, C., Zens, R., Dyer, C., Bojar, O., Constantin, A., and Herbst, E. (2007). \u201cMoses: Open Source Toolkit for Statistical Machine Translation.\u201d In <i>Proceedings of ACL<\/i>, pp. 177\u2013180, Prague, Czech Republic. Association for Computational Linguistics.","DOI":"10.3115\/1557769.1557821"},{"key":"18","unstructured":"Krashen, S. (1977). \u201cSome Issues Relating to The Monitor Model.\u201d <i>On Tesol<\/i>, 77 (144-158)."},{"key":"19","unstructured":"Krashen, S. (1981). \u201cSecond Language Acquisition.\u201d <i>Second Language Learning<\/i>, 3 (7), pp. 19\u201339."},{"key":"20","doi-asserted-by":"crossref","unstructured":"Linzen, T., Dupoux, E., and Goldberg, Y. (2016). \u201cAssessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies.\u201d <i>Transactions of the Association for Computational Linguistics<\/i>, 4, pp. 521\u2013535.","DOI":"10.1162\/tacl_a_00115"},{"key":"21","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, Y., Kasai, J., Hajishirzi, H., and Smith, N. A. (2021). \u201cProbing Across Time: What Does RoBERTa Know and When?\u201d In <i>Findings of the Association for Computational Linguistics: EMNLP 2021<\/i>, pp. 820\u2013842, Punta Cana, Dominican Republic. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2021.findings-emnlp.71"},{"key":"22","doi-asserted-by":"crossref","unstructured":"Manning, C. D. (2015). \u201cLast Words: Computational Linguistics and Deep Learning.\u201d <i>Computational Linguistics<\/i>, 41 (4), pp. 701\u2013707.","DOI":"10.1162\/COLI_a_00239"},{"key":"23","unstructured":"McCoy, R. T., Frank, R., and Linzen, T. (2018). \u201cRevisiting the Poverty of the Stimulus: Hierarchical Generalization without a Hierarchical Bias in Recurrent Neural Networks.\u201d In <i>In Proceedings of CogSci<\/i>, pp. 2093\u20132098, Madison, WI."},{"key":"24","doi-asserted-by":"crossref","unstructured":"Mueller, A., Nicolai, G., Petrou-Zeniou, P., Talmina, N., and Linzen, T. (2020). \u201cCross-Linguistic Syntactic Evaluation of Word Prediction Models.\u201d In <i>Proceedings of ACL<\/i>, pp. 5523\u20135539, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2020.acl-main.490"},{"key":"25","unstructured":"Nation, P. (2014). \u201cHow Much Input Do You Need to Learn the Most Frequent 9,000 Words?\u201d <i>Reading in a Foreign Language<\/i>, 26 (2), p. 2."},{"key":"26","unstructured":"Neubig, G. and Mori, S. (2010). \u201cWord-based Partial Annotation for Efficient Corpus Construction.\u201d In <i>Proceedings of LREC<\/i>, pp. 2723\u20132727, Valletta, Malta. European Language Resources Association (ELRA)."},{"key":"27","unstructured":"Neubig, G., Nakata, Y., and Mori, S. (2011). \u201cPointwise Prediction for Robust, Adaptable Japanese Morphological Analysis.\u201d In <i>Proceedings of ACL<\/i>, pp. 529\u2013533, Portland, Oregon, USA. Association for Computational Linguistics."},{"key":"28","unstructured":"\u5927\u7fbd\u672a\u60a0\uff0c\u6817\u6797\u6a39\u751f\uff0c\u5927\u5185\u5553\u6a39\uff0c\u6e21\u8fba\u592a\u90ce (2022). \u8a00\u8a9e\u30e2\u30c7\u30eb\u306e\u7b2c\u4e8c\u8a00\u8a9e\u7372\u5f97\u52b9\u7387. \u7814\u7a76\u5831\u544a\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\uff08NL\uff09, 2022-NL-254 (22), pp. 1\u20138. [M. Oba et al. (2022). Gengo Moderuno Daini Gengo Kakutoku Koritsu. IPSJ SIG Technical Report, 2022-NL-254 (22), pp. 1\u20138.]."},{"key":"29","unstructured":"\u5927\u7fbd\u672a\u60a0\uff0c\u6817\u6797\u6a39\u751f\uff0c\u5927\u5185\u5553\u6a39\uff0c\u6e21\u8fba\u592a\u90ce (2023). \u8a00\u8a9e\u30e2\u30c7\u30eb\u306e\u7b2c\u4e8c\u8a00\u8a9e\u7372\u5f97. \u8a00\u8a9e\u51e6\u7406\u5b66\u4f1a\u7b2c 29 \u56de\u5e74\u6b21\u5927\u4f1a\u767a\u8868\u8ad6\u6587\u96c6, pp. 651\u2013656. [M. Oba et al. (2023). Gengo Moderuno Daini Gengo Kakutoku. Proceedings of the 29th Annual Meeting of the Association for Natural Language Processing, pp. 651\u2013656.]."},{"key":"30","doi-asserted-by":"crossref","unstructured":"Oba, M., Kuribayashi, T., Ouchi, H., and Watanabe, T. (2023). \u201cSecond Language Acquisition of Neural Language Models.\u201d In <i>Findings of the Association for Computational Linguistics: ACL 2023<\/i>, pp. 13557\u201313572, Toronto, Canada. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2023.findings-acl.856"},{"key":"31","doi-asserted-by":"crossref","unstructured":"Papadimitriou, I. and Jurafsky, D. (2020). \u201cLearning Music Helps You Read: Using Transfer to Study Linguistic Structure in Language Models.\u201d In <i>Proceedings of EMNLP<\/i>, pp. 6829\u20136839, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2020.emnlp-main.554"},{"key":"32","doi-asserted-by":"crossref","unstructured":"P\u00e9rez-Mayos, L., T\u00e1boas Garc\u00eda, A., Mille, S., and Wanner, L. (2021). \u201cAssessing the Syntactic Capabilities of Transformer-based Multilingual Language Models.\u201d In <i>Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021<\/i>, pp. 3799\u20133812, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2021.findings-acl.333"},{"key":"33","doi-asserted-by":"crossref","unstructured":"Pinker, S. and Prince, A. (1988). \u201cOn Language and Connectionism: Analysis of a Parallel Distributed Processing Model of Language Acquisition.\u201d <i>Cognition<\/i>, 28 (1), pp. 73\u2013193.","DOI":"10.1016\/0010-0277(88)90032-7"},{"key":"34","doi-asserted-by":"crossref","unstructured":"Ri, R. and Tsuruoka, Y. (2022). \u201cPretraining with Artificial Language: Studying Transferable Knowledge in Language Models.\u201d In <i>Proceedings of ACL<\/i>, pp. 7302\u20137315, Dublin, Ireland. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2022.acl-long.504"},{"key":"35","doi-asserted-by":"crossref","unstructured":"Rumelhart, D. E. and McClelland, J. L. (1986). \u201cOn Learning the Past Tenses of English Verbs.\u201d In <i>Parallel Distributed Processing: Explorations in the Microstructure of Cognition<\/i>, pp. 216\u2013271. MIT Press, Cambridge, MA.","DOI":"10.7551\/mitpress\/5236.003.0008"},{"key":"36","doi-asserted-by":"crossref","unstructured":"Salazar, J., Liang, D., Nguyen, T. Q., and Kirchhoff, K. (2020). \u201cMasked Language Model Scoring.\u201d In <i>Proceedings of ACL<\/i>, pp. 2699\u20132712, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2020.acl-main.240"},{"key":"37","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., and Birch, A. (2016). \u201cNeural Machine Translation of Rare Words with Subword Units.\u201d In <i>Proceedings of ACL<\/i>, pp. 1715\u20131725, Berlin, Germany. Association for Computational Linguistics.","DOI":"10.18653\/v1\/P16-1162"},{"key":"38","doi-asserted-by":"crossref","unstructured":"Settles, B., Brust, C., Gustafson, E., Hagiwara, M., and Madnani, N. (2018). \u201cSecond Language Acquisition Modeling.\u201d In <i>Proceedings of the 13th Workshop on Innovative Use of NLP for Building Educational Applications<\/i>, pp. 56\u201365, New Orleans, Louisiana. Association for Computational Linguistics.","DOI":"10.18653\/v1\/W18-0506"},{"key":"39","unstructured":"Shi, F., Suzgun, M., Freitag, M., Wang, X., Srivats, S., Vosoughi, S., Chung, H. W., Tay, Y., Ruder, S., Zhou, D., Das, D., and Wei, J. (2023). \u201cLanguage Models are Multilingual Chain-of-Thought Reasoners.\u201d In <i>the 11th International Conference on Learning Representations<\/i>."},{"key":"40","unstructured":"Tiedemann, J. (2012). \u201cParallel Data, Tools and Interfaces in OPUS.\u201d In Chair), N. C. C., Choukri, K., Declerck, T., Dogan, M. U., Maegaard, B., Mariani, J., Odijk, J., and Piperidis, S. (Eds.), <i>Proceedings of LREC<\/i>, pp. 2214\u20132218, Istanbul, Turkey. European Language Resources Association (ELRA)."},{"key":"41","unstructured":"Tyler, C., Zhuowen, T., and Berge, B. (2022). \u201cThe Geometry of Multilingual Language Model Representations.\u201d In <i>Proceedings of EMNLP<\/i>, pp. 119\u2013136, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics."},{"key":"42","unstructured":"Warstadt, A. and Bowman, S. R. (2020). \u201cCan Neural Networks Acquire a Structural Bias from Raw Linguistic Data?\u201d In <i>Proceedings of CogSci<\/i>, pp. 1737\u20131743."},{"key":"43","doi-asserted-by":"crossref","unstructured":"Warstadt, A., Parrish, A., Liu, H., Mohananey, A., Peng, W., Wang, S.-F., and Bowman, S. R. (2020). \u201cBLiMP: The Benchmark of Linguistic Minimal Pairs for English.\u201d <i>Transactions of the Association for Computational Linguistics<\/i>, 8, pp. 377\u2013392.","DOI":"10.1162\/tacl_a_00321"},{"key":"44","unstructured":"Wenzek, G. (2020). \u201cCCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data.\u201d In <i>Proceedings of LREC<\/i>, pp. 4003\u20134012, Marseille, France. European Language Resources Association."},{"key":"45","doi-asserted-by":"crossref","unstructured":"Zhou, G. and Niu, X. (2015). \u201cApproaches to Language Teaching and Learning.\u201d <i>Journal of Language Teaching and Research<\/i>, 6, pp. 798\u2013802.","DOI":"10.17507\/jltr.0604.11"}],"container-title":["Journal of Natural Language Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/jnlp\/31\/2\/31_433\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,15]],"date-time":"2024-06-15T04:28:10Z","timestamp":1718425690000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/jnlp\/31\/2\/31_433\/_article\/-char\/ja\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":45,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024]]}},"URL":"https:\/\/doi.org\/10.5715\/jnlp.31.433","relation":{},"ISSN":["1340-7619","2185-8314"],"issn-type":[{"value":"1340-7619","type":"print"},{"value":"2185-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}