{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:40:01Z","timestamp":1755866401105,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","funder":[{"name":"Postgraduate Research & Practice Innovation Program of Jiangsu Province"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730120","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:25:28Z","timestamp":1752456328000},"page":"116-126","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["\u03bcDS: Multi-Objective Data Snippet Extraction for Dataset Search"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1132-6408","authenticated-orcid":false,"given":"Xiao","family":"Zhou","sequence":"first","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0610-7725","authenticated-orcid":false,"given":"Qiaosheng","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0968-2426","authenticated-orcid":false,"given":"Jiageng","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3539-7776","authenticated-orcid":false,"given":"Gong","family":"Cheng","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88361-4_20"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.14778\/3681954.3681999"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-62466-8_41"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313685"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476311.3476346"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/S00778-019-00564-X"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358096"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657837"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-031--47240--42"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657866"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-030--45439--518"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401044"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018670"},{"key":"e_1_3_2_1_14_1","volume-title":"Personalization of Dataset Retrieval Results using a Metadata-based Data Valuation Method. CoRR","author":"Ebiele Malick","year":"2024","unstructured":"Malick Ebiele, Malika Bendechache, Eamonn Clinton, and Rob Brennan. 2024. Personalization of Dataset Retrieval Results using a Metadata-based Data Valuation Method. CoRR, Vol. abs\/2407.15546 (2024). showeprint[arXiv]2407.15546 https:\/\/arxiv.org\/abs\/2407.15546"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-34129-3_6"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.WEBSEM.2018.11.003"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463261"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the NTCIR-15 Conference.","author":"Kato Makoto P","year":"2020","unstructured":"Makoto P Kato, Hiroaki Ohshima, Ying-Hsang Liu, and Hsin-Liang Chen. 2020. Overview of the NTCIR-15 data search task. In Proceedings of the NTCIR-15 Conference."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.IJHCS.2019.10.004"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025838"},{"key":"e_1_3_2_1_22_1","unstructured":"Chaofan Li MingHao Qin Shitao Xiao Jianlyu Chen Kun Luo Yingxia Shao Defu Lian and Zheng Liu. 2024. Making Text Embedders Few-Shot Learners. arxiv: 2409.15700 [cs.IR] https:\/\/arxiv.org\/abs\/2409.15700"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463238"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531729"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3365575"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.WEBSEM.2021.100647"},{"key":"e_1_3_2_1_27_1","first-page":"957","volume-title":"An Empirical Investigation of Implicit and Explicit Knowledge-Enhanced Methods for Ad Hoc Dataset Retrieval. In Findings of the Association for Computational Linguistics: EMNLP 2023","author":"Luo Weiqing","year":"2023","unstructured":"Weiqing Luo, Qiaosheng Chen, Zhiyang Zhang, Zixian Huang, and Gong Cheng. 2023. An Empirical Investigation of Implicit and Explicit Knowledge-Enhanced Methods for Ad Hoc Dataset Retrieval. In Findings of the Association for Computational Linguistics: EMNLP 2023. Association for Computational Linguistics, 14349--14360. https:\/\/aclanthology.org\/2023.findings-emnlp.957"},{"key":"e_1_3_2_1_28_1","volume-title":"Caiming Xiong, Yingbo Zhou, and Semih Yavuz.","author":"Meng Rui","year":"2024","unstructured":"Rui Meng, Ye Liu, Shafiq Rayhan Joty, Caiming Xiong, Yingbo Zhou, and Semih Yavuz. 2024. SFR-Embedding-2: Advanced Text Embedding with Multi-stage Training. https:\/\/huggingface.co\/Salesforce\/SFR-Embedding-2_R"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964909"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the NTCIR-15 Conference.","author":"Nguyen Phuc","year":"2020","unstructured":"Phuc Nguyen, Kazutoshi Shinoda, Taku Sakamoto, Diana Andreea Petrescu, Hung Nghiep Tran, Atsuhiro Takasu, Akiko Aizawa, and Hideaki Takeda. 2020. Nii table linker at the ntcir-15 data search task: Re-ranking with pre-trained contextualized embeddings, data content, entity-centric, and cluster-based approaches. In Proceedings of the NTCIR-15 Conference."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2020.FINDINGS-EMNLP.63"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the NTCIR-15 Conference.","author":"Okamoto Taku","year":"2020","unstructured":"Taku Okamoto and Hisashi Miyamori. 2020. KSU Systems at the NTCIR-15 Data Search Task. In Proceedings of the NTCIR-15 Conference."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.14778\/3384345.3384346"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626521"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-030-00668--6_9"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","unstructured":"Alfonso Quarati. 2021. Open Government Data: Usage trends and metadata quality. J. Inf. Sci. (2021) 1--24. https:\/\/doi.org\/10.1177\/01655515211027775","DOI":"10.1177\/01655515211027775"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511972"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/916"},{"key":"e_1_3_2_1_39_1","volume-title":"Towards Multi-Facet Snippets for Dataset Search. In ISWC 2019 (CEUR Workshop Proceedings","volume":"6","author":"Wang Xiaxia","year":"2019","unstructured":"Xiaxia Wang, Gong Cheng, and Evgeny Kharlamov. 2019. Towards Multi-Facet Snippets for Dataset Search. In ISWC 2019 (CEUR Workshop Proceedings, Vol. 2465). CEUR-WS.org, 1--6. https:\/\/ceur-ws.org\/Vol-2465\/profiles_paper1.pdf"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-030--88361--41"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3095309"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1162\/DINT_A_00118"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2309.07597"},{"key":"e_1_3_2_1_44_1","volume-title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In ICLR","author":"Xiong Lee","year":"2021","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul N. Bennett, Junaid Ahmed, and Arnold Overwijk. 2021. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In ICLR 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=zeFrfgyZln"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2021.3090276"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583257"}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Padua Italy","acronym":"SIGIR '25"},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3730120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:18:57Z","timestamp":1755865137000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730120"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":46,"alternative-id":["10.1145\/3726302.3730120","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730120","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}