{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T20:45:45Z","timestamp":1743108345853,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819604364"},{"type":"electronic","value":"9789819604371"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-96-0437-1_22","type":"book-chapter","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T16:56:35Z","timestamp":1732640195000},"page":"299-313","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Resource-Efficient Vietnamese Text Summarization: Enhancing Vistral 7B Performance Through Data Filtering, QDoRA\u2019s Low-Memory Footprint, and\u00a0DeepSpeed\u2019s Training Optimization"],"prefix":"10.1007","author":[{"given":"Huy Duc","family":"Nguyen Pham","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dang Tuan","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,27]]},"reference":[{"unstructured":"DeepSpeed: Extreme-scale model training for everyone. https:\/\/www.microsoft.com\/research\/blog\/deepspeed-extreme-scale-model-training-for-everyone. Accessed 24 June 2024","key":"22_CR1"},{"unstructured":"Mistral Finetune Repository (Mistral AI). https:\/\/github.com\/mistralai\/mistral-finetune. Accessed 19 June 2024","key":"22_CR2"},{"unstructured":"Selenium Webdriver. https:\/\/www.selenium.dev\/documentation\/webdriver. Accessed 02 May 2024","key":"22_CR3"},{"unstructured":"Vietnamese News Corpus. https:\/\/huggingface.co\/datasets\/vietgpt\/news_summarization_vi. Accessed 04 May 2024","key":"22_CR4"},{"unstructured":"ZeRO-2 & DeepSpeed: Shattering barriers of deep learning speed & scale. https:\/\/www.microsoft.com\/research\/blog\/zero-2-deepspeed-shattering-barriers-of-deep-learning-speed-scale. Accessed 19 May 2024","key":"22_CR5"},{"doi-asserted-by":"publisher","unstructured":"Ainslie, J., Lee-Thorp, J., de\u00a0Jong, M., Zemlyanskiy, Y., Lebron, F., Sanghai, S.: GQA: training generalized multi-query transformer models from multi-head checkpoints. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 4895\u20134901. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.298","key":"22_CR6","DOI":"10.18653\/v1\/2023.emnlp-main.298"},{"unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol.\u00a033, pp. 1877\u20131901. Curran Associates, Inc. (2020)","key":"22_CR7"},{"unstructured":"Van\u00a0Nguyen, C., et al.: Vistral-7B-Chat - Towards a State-of-the-Art Large Language Model for Vietnamese (2023)","key":"22_CR8"},{"doi-asserted-by":"publisher","unstructured":"Conneau, A., et al.: Unsupervised cross-lingual representation learning at scale. In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 8440\u20138451. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.747","key":"22_CR9","DOI":"10.18653\/v1\/2020.acl-main.747"},{"unstructured":"Dettmers, T., Pagnoni, A., Holtzman, A., Zettlemoyer, L.: QLoRA: efficient finetuning of quantized LLMs. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems, vol.\u00a036, pp. 10088\u201310115. Curran Associates, Inc. (2023)","key":"22_CR10"},{"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: Burstein, J., Doran, C., Solorio, T. (eds.) 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), pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota (2019). https:\/\/doi.org\/10.18653\/v1\/N19-1423","key":"22_CR11","DOI":"10.18653\/v1\/N19-1423"},{"issue":"8","key":"22_CR12","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997). https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","journal-title":"Neural Comput."},{"unstructured":"Jiang, A.Q., et al.: Mistral 7B (2023). arXiv:2310.06825","key":"22_CR13"},{"unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381. Association for Computational Linguistics, Barcelona, Spain (2004)","key":"22_CR14"},{"unstructured":"Liu, S.Y., et al.: DoRA: weight-decomposed low-rank adaptation. In: Salakhutdinov, R., Kolter, Z., Heller, K., Weller, A., Oliver, N., Scarlett, J., Berkenkamp, F. (eds.) Proceedings of the 41st International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0235, pp. 32100\u201332121. PMLR (2024)","key":"22_CR15"},{"key":"22_CR16","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1162\/tacl_a_00343","volume":"8","author":"Y Liu","year":"2020","unstructured":"Liu, Y., et al.: Multilingual denoising pre-training for neural machine translation. Trans. Assoc. Comput. Linguist. 8, 726\u2013742 (2020). https:\/\/doi.org\/10.1162\/tacl_a_00343","journal-title":"Trans. Assoc. Comput. Linguist."},{"doi-asserted-by":"publisher","unstructured":"Nguyen, D.Q., Tuan\u00a0Nguyen, A.: PhoBERT: pre-trained language models for Vietnamese. In: Cohn, T., He, Y., Liu, Y. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 1037\u20131042. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.92","key":"22_CR17","DOI":"10.18653\/v1\/2020.findings-emnlp.92"},{"doi-asserted-by":"publisher","unstructured":"Nguyen, M.T., Nguyen, H.D., Nguyen, T.H.N., Nguyen, V.H.: Towards state-of-the-art baselines for Vietnamese multi-document summarization. In: 2018 10th International Conference on Knowledge and Systems Engineering (KSE), pp. 85\u201390 (2018). https:\/\/doi.org\/10.1109\/KSE.2018.8573420","key":"22_CR18","DOI":"10.1109\/KSE.2018.8573420"},{"doi-asserted-by":"publisher","unstructured":"Nguyen, V.H., Nguyen, T.C., Nguyen, M.T., Hoai, N.X.: VNDS: a Vietnamese dataset for summarization. In: 2019 6th NAFOSTED Conference on Information and Computer Science (NICS), pp. 375\u2013380 (2019). https:\/\/doi.org\/10.1109\/NICS48868.2019.9023886","key":"22_CR19","DOI":"10.1109\/NICS48868.2019.9023886"},{"unstructured":"Pham, H.D.N.: Summary of Vietnamese text based on Transformer. Graduation thesis, Saigon University (2024)","key":"22_CR20"},{"doi-asserted-by":"publisher","unstructured":"Phan, L., Tran, H., Nguyen, H., Trinh, T.H.: ViT5: pretrained text-to-text transformer for Vietnamese language generation. In: Ippolito, D., Li, L.H., Pacheco, M.L., Chen, D., Xue, N. (eds.) Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop, pp. 136\u2013142. Association for Computational Linguistics, Hybrid: Seattle, Washington + Online (2022). https:\/\/doi.org\/10.18653\/v1\/2022.naacl-srw.18","key":"22_CR21","DOI":"10.18653\/v1\/2022.naacl-srw.18"},{"issue":"140","key":"22_CR22","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/SC41405.2020.00024","key":"22_CR23","DOI":"10.1109\/SC41405.2020.00024"},{"doi-asserted-by":"publisher","unstructured":"Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., Liu, Y.: RoFormer: enhanced transformer with rotary position embedding. Neurocomput. 568(C) (2024). https:\/\/doi.org\/10.1016\/j.neucom.2023.127063","key":"22_CR24","DOI":"10.1016\/j.neucom.2023.127063"},{"unstructured":"To, H.Q., Nguyen, K.V., Nguyen, N.L.T., Nguyen, A.G.T.: Monolingual versus multilingual BERTology for Vietnamese extractive multi-document summarization. In: Hu, K., Kim, J.B., Zong, C., Chersoni, E. (eds.) Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation, pp. 692\u2013699. Association for Computational Lingustics, Shanghai, China (2021)","key":"22_CR25"},{"unstructured":"Touvron, H., et al.: LLaMA: open and efficient foundation language models (2023). arXiv:2302.13971","key":"22_CR26"},{"unstructured":"Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models (2023). arXiv:2307.09288","key":"22_CR27"},{"unstructured":"Tran, M.V., Le, H.Q., Can, D.C., Nguyen, Q.A.: Overview of the VLSP 2022 \u2013 Abmusu shared task: a data challenge for Vietnamese abstractive multi-document summarization (2023). arXiv:2311.15525","key":"22_CR28"},{"issue":"4","key":"22_CR29","doi-asserted-by":"publisher","first-page":"893","DOI":"10.1007\/s10579-020-09495-4","volume":"54","author":"NT Tran","year":"2020","unstructured":"Tran, N.T., Nghiem, M.Q., Nguyen, N.T.H., Nguyen, N.L.T., Van Chi, N., Dinh, D.: ViMs: a high-quality Vietnamese dataset for abstractive multi-document summarization. Lang. Resour. Eval. 54(4), 893\u2013920 (2020). https:\/\/doi.org\/10.1007\/s10579-020-09495-4","journal-title":"Lang. Resour. Eval."},{"unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol.\u00a030. Curran Associates, Inc. (2017)","key":"22_CR30"},{"doi-asserted-by":"publisher","unstructured":"Xue, L., et al.: mT5: a massively multilingual pre-trained text-to-text transformer. In: Toutanova, K., (eds.) et al Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 483\u2013498. Association for Computational Linguistics, Online (2021).https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.41","key":"22_CR31","DOI":"10.18653\/v1\/2021.naacl-main.41"}],"container-title":["Communications in Computer and Information Science","Future Data and Security Engineering. Big Data, Security and Privacy, Smart City and Industry 4.0 Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0437-1_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T17:04:29Z","timestamp":1732640669000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0437-1_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819604364","9789819604371"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0437-1_22","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"27 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"FDSE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Future Data and Security Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Binh Duong","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"fdse2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/thefdse.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}