{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:35:36Z","timestamp":1742913336145,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031409776"},{"type":"electronic","value":"9783031409783"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-40978-3_47","type":"book-chapter","created":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T05:01:33Z","timestamp":1692766893000},"page":"442-454","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["llm-japanese-dataset v0: Construction of\u00a0Japanese Chat Dataset for\u00a0Large Language Models and\u00a0Its Methodology"],"prefix":"10.1007","author":[{"given":"Masanori","family":"Hirano","sequence":"first","affiliation":[]},{"given":"Masahiro","family":"Suzuki","sequence":"additional","affiliation":[]},{"given":"Hiroki","family":"Sakaji","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,24]]},"reference":[{"key":"47_CR1","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"47_CR2","unstructured":"Databricks: Dolly (2023). https:\/\/github.com\/databrickslabs\/dolly"},{"key":"47_CR3","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics, pp. 4171\u20134186. Association for Computational Linguistics (2019). https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"47_CR4","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1007\/978-90-481-8847-5_10","volume-title":"Theory and Applications of Ontology: Computer Applications","author":"C Fellbaum","year":"2010","unstructured":"Fellbaum, C.: WordNet. In: Poli, R., Healy, M., Kameas, A. (eds.) Theory and Applications of Ontology: Computer Applications, pp. 231\u2013243. Springer, Dordrecht (2010). https:\/\/doi.org\/10.1007\/978-90-481-8847-5_10"},{"key":"47_CR5","doi-asserted-by":"publisher","unstructured":"Gao, L., et al.: A framework for few-shot language model evaluation (2021). https:\/\/doi.org\/10.5281\/zenodo.5371628","DOI":"10.5281\/zenodo.5371628"},{"key":"47_CR6","unstructured":"Google: Bard (2023). https:\/\/bard.google.com\/"},{"key":"47_CR7","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models (2022). https:\/\/arxiv.org\/abs\/2106.09685"},{"key":"47_CR8","unstructured":"Isahara, H., Bond, F., Uchimoto, K., Utiyama, M., Kanzaki, K.: Development of the Japanese WordNet. In: Language Resources and Evaluation, pp. 2420\u20132423 (2008)"},{"key":"47_CR9","unstructured":"Katsuta, A., Yamamoto, K.: Crowdsourced corpus of sentence simplification with core vocabulary. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation, pp. 461\u2013466 (2018)"},{"key":"47_CR10","doi-asserted-by":"crossref","unstructured":"Kodama, T., Tanaka, R., Kurohashi, S.: Construction of hierarchical structured knowledge-based recommendation dialogue dataset and dialogue system. In: Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, pp. 83\u201392 (2022)","DOI":"10.18653\/v1\/2022.dialdoc-1.9"},{"key":"47_CR11","unstructured":"Kurihara, K., Kawahara, D., Shibata, T.: JGLUE: Japanese general language understanding evaluation. In: Proceedings of the Thirteenth Language Resources and Evaluation Conference, pp. 2957\u20132966 (2022)"},{"key":"47_CR12","unstructured":"Mangrulkar, S., Gugger, S., Debut, L., Belkada, Y., Paul, S.: PEFT: state-of-the-art parameter-efficient fine-tuning methods (2022). https:\/\/github.com\/huggingface\/peft"},{"key":"47_CR13","unstructured":"Maruyama, T., Yamamoto, K.: Simplified corpus with core vocabulary. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation, pp. 1153\u20131160 (2018)"},{"key":"47_CR14","unstructured":"OpenAI: ChatGPT (2023). https:\/\/openai.com\/blog\/chatgpt\/"},{"key":"47_CR15","unstructured":"OpenAI: GPT-4 Technical report (2023). https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"47_CR16","unstructured":"Pryzant, R., Chung, Y., Jurafsky, D., Britz, D.: JESC: Japanese-English subtitle corpus. In: Language Resources and Evaluation Conference pp. 1133\u20131137 (2018)"},{"key":"47_CR17","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018). https:\/\/cdn.openai.com\/research-covers\/language-unsupervised\/language_understanding_paper.pdf"},{"key":"47_CR18","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners (2019). https:\/\/cdn.openai.com\/better-language-models\/language_models_are_unsupervised_multitask_learners.pdf"},{"key":"47_CR19","doi-asserted-by":"crossref","unstructured":"Rajbhandari, S., Rasley, J., Ruwase, O., He, Y.: ZeRO: memory optimizations toward training trillion parameter models. In: SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201316 (2020)","DOI":"10.1109\/SC41405.2020.00024"},{"key":"47_CR20","unstructured":"Riza, H., et\u00a0al.: Introduction of the Asian language treebank. In: 2016 Conference of The Oriental Chapter of International Committee for Coordination and Standardization of Speech Databases and Assessment Techniques, pp. 1\u20136 (2016)"},{"key":"47_CR21","unstructured":"Scao, T.L., et al.: BLOOM: a 176B-parameter open-access multilingual language model (2022). https:\/\/arxiv.org\/abs\/2211.05100"},{"key":"47_CR22","unstructured":"Song, H., Dabre, R., Fujita, A., Kurohashi, S.: Coursera corpus mining and multistage fine-tuning for improving lectures translation. In: Proceedings of the 12th Language Resources and Evaluation Conference, pp. 3640\u20133649 (2020)"},{"key":"47_CR23","unstructured":"Taori, R., et al.: Stanford alpaca: an instruction-following LLaMA model (2023). https:\/\/github.com\/tatsu-lab\/stanford_alpaca"},{"key":"47_CR24","unstructured":"Touvron, H., et al.: LLaMA: open and efficient foundation language models (2023). https:\/\/arxiv.org\/abs\/2302.13971"},{"key":"47_CR25","unstructured":"Utiyama, M.: ParaNatCom\u2014parallel English-Japanese abstract corpus made from nature communications articles (2019). https:\/\/www2.nict.go.jp\/astrec-att\/member\/mutiyama\/paranatcom\/"},{"key":"47_CR26","unstructured":"Vicuna: Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality (2023). https:\/\/vicuna.lmsys.org\/"}],"container-title":["Lecture Notes on Data Engineering and Communications Technologies","Advances in Networked-based Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-40978-3_47","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T05:06:20Z","timestamp":1692767180000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-40978-3_47"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031409776","9783031409783"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-40978-3_47","relation":{},"ISSN":["2367-4512","2367-4520"],"issn-type":[{"type":"print","value":"2367-4512"},{"type":"electronic","value":"2367-4520"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"24 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NBiS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Network-Based Information Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chiang Mai University","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nbis2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/voyager.ce.fit.ac.jp\/conf\/nbis\/2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}