{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T05:45:22Z","timestamp":1743054322673,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031446955"},{"type":"electronic","value":"9783031446962"}],"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\/978-3-031-44696-2_57","type":"book-chapter","created":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T09:03:59Z","timestamp":1696669439000},"page":"732-743","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Unsupervised Clustering for Negative Sampling to Optimize Open-Domain Question Answering Retrieval"],"prefix":"10.1007","author":[{"given":"Feiqing","family":"Zhuang","sequence":"first","affiliation":[]},{"given":"Conghui","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Tiejun","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,8]]},"reference":[{"key":"57_CR1","doi-asserted-by":"crossref","unstructured":"Chen, D., Yih, S.: ACL2020 tutorial: Open-domain Question and Answering. https:\/\/github.com\/danqi\/acl2020-openqa-tutorial. Accessed 5 Jul 2020","DOI":"10.18653\/v1\/2020.acl-tutorials.8"},{"key":"57_CR2","unstructured":"Juan, R.: Using tf-idf to determine word relevance in document queries. In:\u00a0Proceedings of the First Instructional Conference on Machine Learning. vol. 242. no. 1 (2003)"},{"key":"57_CR3","doi-asserted-by":"crossref","unstructured":"Stephen, R., Zaragoza, H.: The probabilistic relevance framework: BM25 and beyond. In: Foundations and Trends\u00ae in Information Retrieval. vol. 3. no. 4, pp. 333\u2013389 (2009)","DOI":"10.1561\/1500000019"},{"key":"57_CR4","unstructured":"Jacob, D., et al.: BERT: Pre-training of deep bidirectional transformers for language understanding (2018).\u00a0arXiv preprint arXiv:1810.04805"},{"key":"57_CR5","unstructured":"Yinhan, L., et al.: RoBERTa: A robustly optimized BERT pretraining approach (2019). arXiv preprint arXiv:1907.11692"},{"key":"57_CR6","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Han, X., Liu, Z., Jiang, X., Sun, M., Liu, Q.: ERNIE: enhanced language representation with informative entities. In:\u00a0Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 1441\u20131451, Florence, Italy. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/P19-1139"},{"key":"57_CR7","doi-asserted-by":"crossref","unstructured":"Robert, T., Walther, G., Hastie, T.: Estimating the number of clusters in a data set via the gap statistic.\u00a0J. R. Stat. Soc. Ser. B (Statistical Methodology)\u00a063(2), 411\u2013423 (2001)","DOI":"10.1111\/1467-9868.00293"},{"key":"57_CR8","unstructured":"Adam, R., Raffel, C., Shazeer, N.: How much knowledge can you pack into the parameters of a language model?\u00a0(2020).\u00a0arXiv preprint arXiv:2002.08910"},{"key":"57_CR9","doi-asserted-by":"crossref","unstructured":"Chen, D., Fisch, A., Weston, J., Bordes, A.:\u00a0Reading wikipedia to answer open-domain questions. In:\u00a0Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1870\u20131879, Vancouver, Canada. Association for Computational Linguistics (2017)","DOI":"10.18653\/v1\/P17-1171"},{"key":"57_CR10","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., et al.:\u00a0Dense passage retrieval for open-domain question answering. In:\u00a0Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 6769\u20136781, Online. Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"57_CR11","doi-asserted-by":"crossref","unstructured":"Yamada, I., Asai, A., Hajishirzi, H.: Efficient passage retrieval with hashing for open-domain question answering. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pp. 979\u2013986, Online. Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.acl-short.123"},{"key":"57_CR12","doi-asserted-by":"crossref","unstructured":"Izacard, G., Grave, E.: Leveraging passage retrieval with generative models for open domain question answering. In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 874\u2013880, Online. Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"57_CR13","doi-asserted-by":"crossref","unstructured":"Yu, D., et al.: KG-FiD: infusing knowledge graph in fusion-in-decoder for open-domain question answering. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 4961\u20134974, Dublin, Ireland. Association for Computational Linguistics (2022)","DOI":"10.18653\/v1\/2022.acl-long.340"},{"key":"57_CR14","doi-asserted-by":"crossref","unstructured":"Seo, M., Lee, J., Kwiatkowski, T., Parikh, A., Farhadi, A., Hajishirzi, H.: Real-time open-domain question answering with dense-sparse phrase index. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 4430\u20134441, Florence, Italy. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/P19-1436"},{"key":"57_CR15","doi-asserted-by":"crossref","unstructured":"Qi, P., Lee, H., Sido, T., Manning, C.: Answering open-domain questions of varying reasoning steps from text. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 3599\u20133614, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.292"},{"key":"57_CR16","unstructured":"Lee, X., et al.: Approximate nearest neighbor negative contrastive learning for dense text retrieval (2020).\u00a0arXiv preprint arXiv:2007.00808"},{"key":"57_CR17","unstructured":"Guillaume, A., et al.: Variance reduction in sgd by distributed importance sampling (2015).\u00a0arXiv preprint arXiv:1511.06481"},{"key":"57_CR18","doi-asserted-by":"crossref","unstructured":"Tom, K., et al.: Natural questions: a benchmark for question answering research.\u00a0Trans. Assoc. Comput. Linguist. 7, 453\u2013466 (2019)","DOI":"10.1162\/tacl_a_00276"},{"key":"57_CR19","unstructured":"Mandar, J., et al.: TriviaQA: A large scale distantly supervised challenge dataset for reading comprehension (2017).\u00a0arXiv preprint arXiv:1705.03551"},{"key":"57_CR20","unstructured":"Tongzhou, W., Isola, P.: Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In: International Conference on Machine Learning. PMLR (2020)"},{"key":"57_CR21","unstructured":"Yingqi, Q., et al.: RocketQA: An optimized training approach to dense passage retrieval for open-domain question answering (2020).\u00a0arXiv preprint arXiv:2010.08191"},{"key":"57_CR22","unstructured":"Wei, Y., et al.: End-to-end open-domain question answering with bertserini (2019).\u00a0arXiv preprint arXiv:1902.01718"},{"key":"57_CR23","doi-asserted-by":"crossref","unstructured":"Soyeong, J., et al.: Augmenting document representations for dense retrieval with interpolation and perturbation (2022).\u00a0arXiv preprint arXiv:2203.07735","DOI":"10.18653\/v1\/2022.acl-short.48"},{"key":"57_CR24","doi-asserted-by":"crossref","unstructured":"Wang, S., Yu, M., Guo, X., et al.: R3: reinforced ranker-reader for open-domain question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12053"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44696-2_57","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T09:12:30Z","timestamp":1696669950000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44696-2_57"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031446955","9783031446962"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44696-2_57","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"8 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Foshan","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2023\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Softconf","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"478","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"143","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"30% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}