{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T07:02:36Z","timestamp":1762326156275,"version":"3.41.2"},"publisher-location":"Singapore","reference-count":18,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819500192"},{"type":"electronic","value":"9789819500208"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-95-0020-8_43","type":"book-chapter","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T09:17:07Z","timestamp":1753262227000},"page":"507-518","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Semantic-Structural Synergistic Chunking Method for Enhancing Domain-Specific LLM Fine-Tuning"],"prefix":"10.1007","author":[{"given":"Baosheng","family":"Yin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dapeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenlai","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naiyu","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,24]]},"reference":[{"key":"43_CR1","unstructured":"Achiam, J., et al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"43_CR2","unstructured":"Parthasarathy, V.B., Zafar, A., Khan, A., Shahid, A.: The ultimate guide to fine-tuning llms from basics to breakthroughs: An exhaustive review of technologies, research, best practices, applied research challenges and opportunities. arXiv preprint arXiv:2408.13296 (2024)"},{"key":"43_CR3","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pp. 311--318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"43_CR4","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text summarization branches out, pp. 74--81 (2004)"},{"key":"43_CR5","unstructured":"Deepak, P., Visweswariah, K., Wiratunga, N., Sani, S.: Two-part segmentation of text documents (2012)"},{"issue":"8","key":"43_CR6","first-page":"1567","volume":"30","author":"M Brown","year":"2018","unstructured":"Brown, M., Davis, S.: Fixed-size chunking for efficient text processing. IEEE Trans. Knowl. Data Eng. 30(8), 1567\u20131580 (2018)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"43_CR7","unstructured":"Verma, P.: S2 chunking: a hybrid framework for document segmentation through integrated spatial and semantic analysis. arXiv preprint arXiv:2501.05485"},{"key":"43_CR8","doi-asserted-by":"crossref","unstructured":"Park, S.B., Zhang, B.T.: Text chunking by combining hand-crafted rules and memory-based learning. In: Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, pp. 497--504 (2003)","DOI":"10.3115\/1075096.1075159"},{"issue":"24","key":"43_CR9","volume":"7","author":"P Kherwa","year":"2020","unstructured":"Kherwa, P., Bansal, P.: Topic modeling: a comprehensive review. EAI Endorsed Trans. Scalable Inf. Syst. 7(24), e2 (2020)","journal-title":"EAI Endorsed Trans. Scalable Inf. Syst."},{"key":"43_CR10","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: Human Language Technologies, volume 1 (long and short papers), pp. 4171\u20134186 (2019)"},{"key":"43_CR11","unstructured":"AI, L.: Langchain: Build context-aware reasoning applications. GitHub repository (2023). https:\/\/github.com\/langchain-ai\/langchain. Accessed 07 Apr 2025"},{"key":"43_CR12","unstructured":"Kamradt, G.: Semantic chunking. Online resource (2024). https:\/\/github.com\/FullStackRetrieval-com\/RetrievalTutorials. Accessed 07 Apr 2025"},{"key":"43_CR13","unstructured":"Zheng, Z., et al.: Attention heads of large language models: a survey. arXiv preprint arXiv:2409.03752 (2024)"},{"key":"43_CR14","doi-asserted-by":"crossref","unstructured":"Duarte, A.V., Marques, J.D.S., Gra\u00e7a, M., Freire, M., Li, L., Oliveira, A.L.: LumberChunker: long-form narrative document segmentation. In: Findingds of the Association for Computational Linguistice:EMNLP 2024, Miami, Florida, USA, pp. 6473\u20136486. Association for Computational Linguistics (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.377"},{"key":"43_CR15","unstructured":"Subramani, N., Matton, A., Greaves, M., Lam, A.: A survey of deep learning approaches for ocr and document understanding. In: NeurIPS 2020 Workshop: ML Retrospectives, Suervy & Meta-analyses (ML-RSA) (2020)"},{"key":"43_CR16","unstructured":"Yang, A., et al.: Qwen2.5 technical report. arXiv preprint arXiv:2412.15115 (2024)"},{"issue":"2","key":"43_CR17","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu, E.J., et al.: Lora: Low-rank adaptation of large language models. ICLR 1(2), 3 (2022)","journal-title":"ICLR"},{"key":"43_CR18","unstructured":"Vasiliev, Y.: Natural language processing with Python and spaCy: a practical introduction. No Starch Press (2020)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-0020-8_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T22:13:36Z","timestamp":1753308816000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-0020-8_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819500192","9789819500208"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-0020-8_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}