{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T22:22:50Z","timestamp":1775082170721,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819584192","type":"print"},{"value":"9789819584208","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-8420-8_16","type":"book-chapter","created":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:13:59Z","timestamp":1775074439000},"page":"198-210","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing RAPTOR in RAG Systems: Semantic Segmentation for Improved Initial Chunking"],"prefix":"10.1007","author":[{"given":"Xin","family":"Wan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodong","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tingjun","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,2]]},"reference":[{"key":"16_CR1","unstructured":"Lewis, P., et al.: Retrieval augmented generation for knowledge intensive NLP tasks. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 9459\u20139474 (2020)"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 6769\u20136781 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"16_CR3","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few shot learners. Adv. Neural Inform. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural Inform. Process. Syst."},{"issue":"240","key":"16_CR4","first-page":"1","volume":"24","author":"A Chowdhery","year":"2023","unstructured":"Chowdhery, A., et al.: Palm: scaling language modeling with path-ways. J. Mach. Learn. Res. 24(240), 1\u2013113 (2023)","journal-title":"J. Mach. Learn. Res."},{"key":"16_CR5","first-page":"153","volume":"12","author":"NF Liu","year":"2024","unstructured":"Liu, N.F., et al.: Lost in the middle: how language models use long contexts. Trans. Assoc. Comput. Linguist. 12, 153\u2013173 (2024)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Barnett, S., et al.: Seven failure points when engineering a retrieval augmented generation system. arXiv preprint arXiv:2401.05856 (2024)","DOI":"10.1145\/3644815.3644945"},{"key":"16_CR7","unstructured":"Sarthi, P., Abdullah, S., Tuli, A., Khanna, S., Goldie, A., Manning, C.D.: Raptor: recursive abstractive processing for tree organized retrieval. In: Proceedings of the the Twelfth International Conference on Learning Representations, Vienna, Austria (2024)"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Nair, I., et al.: A neural CRF based hierarchical approach for linear text segmentation. In: Proceedings of the Findings of the Association for Computational Linguistics: EACL 2023, Dubrovnik, Croatia, pp. 883\u2013893 (2023)","DOI":"10.18653\/v1\/2023.findings-eacl.65"},{"issue":"1","key":"16_CR9","first-page":"33","volume":"23","author":"MA Hearst","year":"1997","unstructured":"Hearst, M.A.: TextTiling: a quantitative approach to discourse segmentation. Comput. Linguist. 23(1), 33\u201373 (1997)","journal-title":"Comput. Linguist."},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence BERT: sentence embeddings using Siamese BERT networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, Hong Kong, China, Association for Computational Linguistics, pp. 3982\u20133992 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Aggarwal, C.C., Hinneburg, A., Keim, D.A.: On the surprising behavior of distance metrics in high dimensional space. In: Proceedings of the 8th International Conference on Database Theory (ICDT 2001), London, UK, pp. 420\u2013434 (2001)","DOI":"10.1007\/3-540-44503-X_27"},{"issue":"29","key":"16_CR12","doi-asserted-by":"publisher","first-page":"861","DOI":"10.21105\/joss.00861","volume":"3","author":"L McInnes","year":"2018","unstructured":"McInnes, L., Healy, J., Melville, J.: UMAP: uniform manifold approximation and projection for dimension reduction. J. Open Source Softw. 3(29), 861 (2018)","journal-title":"J. Open Source Softw."},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Aggarwal, C.C., Zhai, C.: A survey of text clustering algorithms. In: Mining Text Data, pp. 77\u2013128 (2012)","DOI":"10.1007\/978-1-4614-3223-4_4"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Zhang, S., Wan, D., Bansal, M.: Extractive is not faithful: an investigation of broad unfaith-fulness problems in extractive summarization. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, Toronto, Canada, pp. 2153\u20132174 (2023)","DOI":"10.18653\/v1\/2023.acl-long.120"},{"key":"16_CR15","unstructured":"Gidi, C., Cohen, S.B.: Query-focused abstractive summarization: a survey. In: Proceedings of the 29th International Conference on Computational Linguistics, pp. 3236\u20133248 (2022)"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Cao, S., Wang, L.: HIBRIDS: attention with hierarchical biases for structure aware long document summarization. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, Dublin, Ireland, pp. 786\u2013807 (2022)","DOI":"10.18653\/v1\/2022.acl-long.58"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Pang, R. Y., et al.: QuALITY: question answering with long in-put texts, yes! In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Seattle, United States, pp. 5336\u20135358 (2022)","DOI":"10.18653\/v1\/2022.naacl-main.391"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Chen, J., Xiao, S., Zhang, P., Luo, K., Lian, D., Liu, Z.: BGE M3-embedding: multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv preprint arXiv:2402.03216 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"16_CR19","unstructured":"Chen, J., Goldberg, Y., Zbib, R.: From chunks to propositions: meaning-based content representation for RAG. arXiv preprint arXiv:2405.02503 (2024)"},{"key":"16_CR20","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1162\/tacl_a_00324","volume":"8","author":"Z Jiang","year":"2020","unstructured":"Jiang, Z., Xu, F.F., Araki, J., Neubig, G.: How can we know what language models know? Trans. Assoc. Comput. Linguist. 8, 423\u2013438 (2020)","journal-title":"Trans. Assoc. Comput. Linguist."}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-8420-8_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:14:01Z","timestamp":1775074441000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-8420-8_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819584192","9789819584208"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-8420-8_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","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":"30 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ieee-cybermatics.org\/2025\/ica3pp\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}