{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T05:26:42Z","timestamp":1755926802779,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T00:00:00Z","timestamp":1697846400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Youth Innovation Promotion Association CAS","award":["2021100"],"award-info":[{"award-number":["2021100"]}]},{"name":"Ant Innovative Research Program"},{"name":"Lenovo-CAS Joint Lab Youth Scientist Project"},{"name":"National Natural Science Foundation of China (NSFC)","award":["61902381"],"award-info":[{"award-number":["61902381"]}]},{"name":"Project","award":["JCKY2022130C039,2021QY1701"],"award-info":[{"award-number":["JCKY2022130C039,2021QY1701"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,21]]},"DOI":"10.1145\/3583780.3615157","type":"proceedings-article","created":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T07:45:42Z","timestamp":1697874342000},"page":"4300-4304","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Pre-training with Aspect-Content Text Mutual Prediction for Multi-Aspect Dense Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4570-6359","authenticated-orcid":false,"given":"Xiaojie","family":"Sun","sequence":"first","affiliation":[{"name":"ICT, CAS & University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5123-4999","authenticated-orcid":false,"given":"Keping","family":"Bi","sequence":"additional","affiliation":[{"name":"ICT, CAS & University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9509-8674","authenticated-orcid":false,"given":"Jiafeng","family":"Guo","sequence":"additional","affiliation":[{"name":"ICT, CAS & University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5511-9370","authenticated-orcid":false,"given":"Xinyu","family":"Ma","sequence":"additional","affiliation":[{"name":"ICT, CAS & University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4317-2702","authenticated-orcid":false,"given":"Yixing","family":"Fan","sequence":"additional","affiliation":[{"name":"ICT, CAS & University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1213-4690","authenticated-orcid":false,"given":"Hongyu","family":"Shan","sequence":"additional","affiliation":[{"name":"Ant Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9964-6298","authenticated-orcid":false,"given":"Qishen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ant Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9478-8107","authenticated-orcid":false,"given":"Zhongyi","family":"Liu","sequence":"additional","affiliation":[{"name":"Ant Group, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2023,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.3390\/a11090137"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3361738"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271801"},{"key":"e_1_3_2_1_4_1","volume-title":"Pre-training Tasks for Embedding-based Large-scale Retrieval. In 8th International Conference on Learning Representations, ICLR 2020","author":"Chang Wei-Cheng","year":"2020","unstructured":"Wei-Cheng Chang , Felix X. Yu , Yin-Wen Chang , Yiming Yang , and Sanjiv Kumar . 2020 . Pre-training Tasks for Embedding-based Large-scale Retrieval. In 8th International Conference on Learning Representations, ICLR 2020 , Addis Ababa, Ethiopia, April 26--30 , 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=rkg-mA4FDr Wei-Cheng Chang, Felix X. Yu, Yin-Wen Chang, Yiming Yang, and Sanjiv Kumar. 2020. Pre-training Tasks for Embedding-based Large-scale Retrieval. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26--30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=rkg-mA4FDr"},{"key":"e_1_3_2_1_5_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. CoRR","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2018 . BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. CoRR , Vol. abs\/ 1810 .04805 (2018). showeprint[arXiv]1810.04805 http:\/\/arxiv.org\/abs\/1810.04805 Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. CoRR , Vol. abs\/1810.04805 (2018). showeprint[arXiv]1810.04805 http:\/\/arxiv.org\/abs\/1810.04805"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000100"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.75"},{"key":"e_1_3_2_1_8_1","volume-title":"Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval. CoRR","author":"Gao Luyu","year":"2022","unstructured":"Luyu Gao , Xueguang Ma , Jimmy Lin , and Jamie Callan . 2022 . Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval. CoRR , Vol. abs\/ 2203 .05765 (2022). https:\/\/doi.org\/10.48550\/arXiv.2203.05765 showeprint[arXiv]2203.05765 10.48550\/arXiv.2203.05765 Luyu Gao, Xueguang Ma, Jimmy Lin, and Jamie Callan. 2022. Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval. CoRR , Vol. abs\/2203.05765 (2022). https:\/\/doi.org\/10.48550\/arXiv.2203.05765 showeprint[arXiv]2203.05765"},{"key":"e_1_3_2_1_9_1","volume-title":"SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Sebastian","year":"2021","unstructured":"Sebastian Hofst\"a tter, Sheng-Chieh Lin , Jheng-Hong Yang , Jimmy Lin , and Allan Hanbury . 2021 . Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling . In SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval , Virtual Event, Canada, July 11--15 , 2021, Fernando Diaz, Chirag Shah, Torsten Suel, Pablo Castells, Rosie Jones, and Tetsuya Sakai (Eds.). ACM, 113--122. https:\/\/doi.org\/10.1145\/3404835.3462891 10.1145\/3404835.3462891 Sebastian Hofst\"a tter, Sheng-Chieh Lin, Jheng-Hong Yang, Jimmy Lin, and Allan Hanbury. 2021. Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling. In SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, Canada, July 11--15, 2021, Fernando Diaz, Chirag Shah, Torsten Suel, Pablo Castells, Rosie Jones, and Tetsuya Sakai (Eds.). ACM, 113--122. https:\/\/doi.org\/10.1145\/3404835.3462891"},{"key":"e_1_3_2_1_10_1","volume-title":"Real-time Inference in Multi-sentence Tasks with Deep Pretrained Transformers. CoRR","author":"Humeau Samuel","year":"1969","unstructured":"Samuel Humeau , Kurt Shuster , Marie-Anne Lachaux , and Jason Weston . 2019. Real-time Inference in Multi-sentence Tasks with Deep Pretrained Transformers. CoRR , Vol. abs\/ 1905 .0 1969 (2019). showeprint[arXiv]1905.01969 http:\/\/arxiv.org\/abs\/1905.01969 Samuel Humeau, Kurt Shuster, Marie-Anne Lachaux, and Jason Weston. 2019. Real-time Inference in Multi-sentence Tasks with Deep Pretrained Transformers. CoRR , Vol. abs\/1905.01969 (2019). showeprint[arXiv]1905.01969 http:\/\/arxiv.org\/abs\/1905.01969"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_12_1","volume-title":"Multi-Aspect Dense Retrieval. In KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Kong Weize","year":"2022","unstructured":"Weize Kong , Swaraj Khadanga , Cheng Li , Shaleen Kumar Gupta , Mingyang Zhang , Wensong Xu , and Michael Bendersky . 2022 . Multi-Aspect Dense Retrieval. In KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining , Washington, DC, USA, August 14 - 18 , 2022, Aidong Zhang and Huzefa Rangwala (Eds.). ACM, 3178--3186. https:\/\/doi.org\/10.1145\/3534678.3539137 10.1145\/3534678.3539137 Weize Kong, Swaraj Khadanga, Cheng Li, Shaleen Kumar Gupta, Mingyang Zhang, Wensong Xu, and Michael Bendersky. 2022. Multi-Aspect Dense Retrieval. In KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, August 14 - 18, 2022, Aidong Zhang and Huzefa Rangwala (Eds.). ACM, 3178--3186. https:\/\/doi.org\/10.1145\/3534678.3539137"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1612"},{"key":"e_1_3_2_1_14_1","volume-title":"Pretrained Transformers for Text Ranking: BERT and Beyond","author":"Lin Jimmy","year":"2021","unstructured":"Jimmy Lin , Rodrigo Nogueira , and Andrew Yates . 2021. Pretrained Transformers for Text Ranking: BERT and Beyond . Morgan & Claypool Publishers . https:\/\/doi.org\/10.2200\/S01123ED1V01Y 2021 08HLT053 10.2200\/S01123ED1V01Y202108HLT053 Jimmy Lin, Rodrigo Nogueira, and Andrew Yates. 2021. Pretrained Transformers for Text Ranking: BERT and Beyond. Morgan & Claypool Publishers. https:\/\/doi.org\/10.2200\/S01123ED1V01Y202108HLT053"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.220"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531772"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557527"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380046"},{"key":"e_1_3_2_1_19_1","volume-title":"Fran Valero, Nikhil Rao, Hugo Zaragoza, Sambaran Bandyopadhyay, Arnab Biswas, Anlu Xing, and Karthik Subbian.","author":"Reddy Chandan K.","year":"2022","unstructured":"Chandan K. Reddy , Llu'i s M\u00e0 rquez , Fran Valero, Nikhil Rao, Hugo Zaragoza, Sambaran Bandyopadhyay, Arnab Biswas, Anlu Xing, and Karthik Subbian. 2022 . Shopping Queries Dataset: A Large-Scale ESCI Benchmark for Improving Product Search. CoRR , Vol. abs\/ 2206 .06588 (2022). https:\/\/doi.org\/10.48550\/arXiv.2206.06588 showeprint[arXiv]2206.06588 10.48550\/arXiv.2206.06588 Chandan K. Reddy, Llu'i s M\u00e0 rquez, Fran Valero, Nikhil Rao, Hugo Zaragoza, Sambaran Bandyopadhyay, Arnab Biswas, Anlu Xing, and Karthik Subbian. 2022. Shopping Queries Dataset: A Large-Scale ESCI Benchmark for Improving Product Search. CoRR , Vol. abs\/2206.06588 (2022). https:\/\/doi.org\/10.48550\/arXiv.2206.06588 showeprint[arXiv]2206.06588"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767724"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the 2004 ACM CIKM International Conference on Information and Knowledge Management","author":"Robertson Stephen E.","year":"2004","unstructured":"Stephen E. Robertson , Hugo Zaragoza , and Michael J. Taylor . 2004. Simple BM25 extension to multiple weighted fields . In Proceedings of the 2004 ACM CIKM International Conference on Information and Knowledge Management , Washington, DC, USA, November 8--13 , 2004 , David A. Grossman, Luis Gravano, ChengXiang Zhai, Otthein Herzog, and David A. Evans (Eds.). ACM, 42--49. https:\/\/doi.org\/10.1145\/1031171.1031181 10.1145\/1031171.1031181 Stephen E. Robertson, Hugo Zaragoza, and Michael J. Taylor. 2004. Simple BM25 extension to multiple weighted fields. In Proceedings of the 2004 ACM CIKM International Conference on Information and Knowledge Management, Washington, DC, USA, November 8--13, 2004, David A. Grossman, Luis Gravano, ChengXiang Zhai, Otthein Herzog, and David A. Evans (Eds.). ACM, 42--49. https:\/\/doi.org\/10.1145\/1031171.1031181"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583254"},{"key":"e_1_3_2_1_24_1","volume-title":"ERNIE: Enhanced Representation through Knowledge Integration. CoRR","author":"Sun Yu","year":"2019","unstructured":"Yu Sun , Shuohuan Wang , Yu-Kun Li , Shikun Feng , Xuyi Chen , Han Zhang , Xin Tian , Danxiang Zhu , Hao Tian , and Hua Wu . 2019 . ERNIE: Enhanced Representation through Knowledge Integration. CoRR , Vol. abs\/ 1904 .09223 (2019). showeprint[arXiv]1904.09223 http:\/\/arxiv.org\/abs\/1904.09223 Yu Sun, Shuohuan Wang, Yu-Kun Li, Shikun Feng, Xuyi Chen, Han Zhang, Xin Tian, Danxiang Zhu, Hao Tian, and Hua Wu. 2019. ERNIE: Enhanced Representation through Knowledge Integration. CoRR , Vol. abs\/1904.09223 (2019). showeprint[arXiv]1904.09223 http:\/\/arxiv.org\/abs\/1904.09223"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.35"},{"key":"e_1_3_2_1_26_1","volume-title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In 9th International Conference on Learning Representations, ICLR 2021","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 9th International Conference on Learning Representations, ICLR 2021 , Virtual Event, Austria, May 3--7 , 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=zeFrfgyZln 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 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3--7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=zeFrfgyZln"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159730"},{"key":"e_1_3_2_1_28_1","volume-title":"Optimizing Dense Retrieval Model Training with Hard Negatives. In SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Zhan Jingtao","year":"2021","unstructured":"Jingtao Zhan , Jiaxin Mao , Yiqun Liu , Jiafeng Guo , Min Zhang , and Shaoping Ma . 2021 . Optimizing Dense Retrieval Model Training with Hard Negatives. In SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval , Virtual Event, Canada, July 11--15 , 2021, , Fernando Diaz, Chirag Shah, Torsten Suel, Pablo Castells, Rosie Jones, and Tetsuya Sakai (Eds.). ACM, 1503--1512. https:\/\/doi.org\/10.1145\/3404835.3462880 10.1145\/3404835.3462880 Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, and Shaoping Ma. 2021. Optimizing Dense Retrieval Model Training with Hard Negatives. In SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, Canada, July 11--15, 2021, , Fernando Diaz, Chirag Shah, Torsten Suel, Pablo Castells, Rosie Jones, and Tetsuya Sakai (Eds.). ACM, 1503--1512. https:\/\/doi.org\/10.1145\/3404835.3462880"},{"key":"e_1_3_2_1_29_1","volume-title":"RepBERT: Contextualized Text Embeddings for First-Stage Retrieval. CoRR","author":"Zhan Jingtao","year":"2020","unstructured":"Jingtao Zhan , Jiaxin Mao , Yiqun Liu , Min Zhang , and Shaoping Ma. 2020. RepBERT: Contextualized Text Embeddings for First-Stage Retrieval. CoRR , Vol. abs\/ 2006 .15498 ( 2020 ). showeprint[arXiv]2006.15498 https:\/\/arxiv.org\/abs\/2006.15498 Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Min Zhang, and Shaoping Ma. 2020. RepBERT: Contextualized Text Embeddings for First-Stage Retrieval. CoRR , Vol. abs\/2006.15498 (2020). showeprint[arXiv]2006.15498 https:\/\/arxiv.org\/abs\/2006.15498"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the SIGIR 2019 Workshop on eCommerce, co-located with the 42st International ACM SIGIR Conference on Research and Development in Information Retrieval, eCom@SIGIR","author":"Zhang Hongchun","year":"2019","unstructured":"Hongchun Zhang , Tianyi Wang , Xiaonan Meng , and Yi Hu. 2019. Improving Semantic Matching via Multi-Task Learning in E-Commerce . In Proceedings of the SIGIR 2019 Workshop on eCommerce, co-located with the 42st International ACM SIGIR Conference on Research and Development in Information Retrieval, eCom@SIGIR 2019 , Paris, France, July 25, 2019 (CEUR Workshop Proceedings , Vol. 2410), , Jon Degenhardt, Surya Kallumadi, Utkarsh Porwal, and Andrew Trotman (Eds.). CEUR-WS.org. http:\/\/ceur-ws.org\/Vol-2410\/paper 2 .pdf Hongchun Zhang, Tianyi Wang, Xiaonan Meng, and Yi Hu. 2019. Improving Semantic Matching via Multi-Task Learning in E-Commerce. In Proceedings of the SIGIR 2019 Workshop on eCommerce, co-located with the 42st International ACM SIGIR Conference on Research and Development in Information Retrieval, eCom@SIGIR 2019, Paris, France, July 25, 2019 (CEUR Workshop Proceedings, Vol. 2410), , Jon Degenhardt, Surya Kallumadi, Utkarsh Porwal, and Andrew Trotman (Eds.). CEUR-WS.org. http:\/\/ceur-ws.org\/Vol-2410\/paper2.pdf"}],"event":{"name":"CIKM '23: The 32nd ACM International Conference on Information and Knowledge Management","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Birmingham United Kingdom","acronym":"CIKM '23"},"container-title":["Proceedings of the 32nd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583780.3615157","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3583780.3615157","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:42Z","timestamp":1750178202000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583780.3615157"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,21]]},"references-count":30,"alternative-id":["10.1145\/3583780.3615157","10.1145\/3583780"],"URL":"https:\/\/doi.org\/10.1145\/3583780.3615157","relation":{},"subject":[],"published":{"date-parts":[[2023,10,21]]},"assertion":[{"value":"2023-10-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}