{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:03:35Z","timestamp":1750309415204,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,21]]},"DOI":"10.1145\/3627673.3679971","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:11Z","timestamp":1729452851000},"page":"3917-3921","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-DSI: Non-deterministic Identifier and Concept Alignment for Differentiable Search Index"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0394-0675","authenticated-orcid":false,"given":"Yu-Ze","family":"Liu","sequence":"first","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1753-8099","authenticated-orcid":false,"given":"Jyun-Yu","family":"Jiang","sequence":"additional","affiliation":[{"name":"Amazon Search, Palo Alto, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5892-0385","authenticated-orcid":false,"given":"Pu-Jen","family":"Cheng","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"31668","article-title":"Autoregressive search engines: Generating substrings as document identifiers","volume":"35","author":"Bevilacqua Michele","year":"2022","unstructured":"Michele Bevilacqua, Giuseppe Ottaviano, Patrick Lewis, Scott Yih, Sebastian Riedel, and Fabio Petroni. 2022. Autoregressive search engines: Generating substrings as document identifiers. Advances in Neural Information Processing Systems 35 (2022), 31668--31683.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_2_1","volume-title":"Autoregressive entity retrieval. arXiv preprint arXiv:2010.00904","author":"Cao Nicola De","year":"2020","unstructured":"Nicola De Cao, Gautier Izacard, Sebastian Riedel, and Fabio Petroni. 2020. Autoregressive entity retrieval. arXiv preprint arXiv:2010.00904 (2020)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSET59111.2023.10295108"},{"key":"e_1_3_2_1_4_1","volume-title":"Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906 (2020)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_1_7_1","volume-title":"Nonparametric decoding for generative retrieval. arXiv preprint arXiv:2210.02068","author":"Lee Hyunji","year":"2022","unstructured":"Hyunji Lee, Jaeyoung Kim, Hoyeon Chang, Hanseok Oh, Sohee Yang, Vlad Karpukhin, Yi Lu, and Minjoon Seo. 2022. Nonparametric decoding for generative retrieval. arXiv preprint arXiv:2210.02068 (2022)."},{"key":"e_1_3_2_1_8_1","volume-title":"Learning dense representations of phrases at scale. arXiv preprint arXiv:2012.12624","author":"Lee Jinhyuk","year":"2020","unstructured":"Jinhyuk Lee, Mujeen Sung, Jaewoo Kang, and Danqi Chen. 2020. Learning dense representations of phrases at scale. arXiv preprint arXiv:2012.12624 (2020)."},{"key":"e_1_3_2_1_9_1","volume-title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461","author":"Lewis Mike","year":"2019","unstructured":"Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, and Luke Zettlemoyer. 2019. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.366"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28717"},{"key":"e_1_3_2_1_12_1","volume-title":"Updating transformer memory with new documents. arXiv preprint arXiv:2212.09744","author":"Mehta Sanket Vaibhav","year":"2022","unstructured":"Sanket Vaibhav Mehta, Jai Gupta, Yi Tay, Mostafa Dehghani, Vinh Q Tran, Jinfeng Rao, Marc Najork, Emma Strubell, and Donald Metzler. 2022. DSI++: Updating transformer memory with new documents. arXiv preprint arXiv:2212.09744 (2022)."},{"volume-title":"Acm sigir forum","author":"Metzler Donald","key":"e_1_3_2_1_13_1","unstructured":"Donald Metzler, Yi Tay, Dara Bahri, and Marc Najork. 2021. Rethinking search: making domain experts out of dilettantes. In Acm sigir forum, Vol. 55. ACM New York, NY, USA, 1--27."},{"key":"e_1_3_2_1_14_1","unstructured":"Tri Nguyen Mir Rosenberg Xia Song Jianfeng Gao Saurabh Tiwary Rangan Majumder and Li Deng. 2016. Ms marco: A human-generated machine reading comprehension dataset. (2016)."},{"key":"e_1_3_2_1_15_1","volume-title":"Generative retrieval as dense retrieval. arXiv preprint arXiv:2306.11397","author":"Nguyen Thong","year":"2023","unstructured":"Thong Nguyen and Andrew Yates. 2023. Generative retrieval as dense retrieval. arXiv preprint arXiv:2306.11397 (2023)."},{"key":"e_1_3_2_1_16_1","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research 21, 140 (2020), 1--67.","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_17_1","volume-title":"Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084","author":"Reimers Nils","year":"2019","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)."},{"key":"e_1_3_2_1_18_1","volume-title":"Jing Liu, Hua Wu, Ji-Rong Wen, and Haifeng Wang.","author":"Ren Ruiyang","year":"2023","unstructured":"Ruiyang Ren, Wayne Xin Zhao, Jing Liu, Hua Wu, Ji-Rong Wen, and Haifeng Wang. 2023. TOME: A two-stage approach for model-based retrieval. arXiv preprint arXiv:2305.11161 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"Learning to tokenize for generative retrieval. Advances in Neural Information Processing Systems 36","author":"Sun Weiwei","year":"2024","unstructured":"Weiwei Sun, Lingyong Yan, Zheng Chen, Shuaiqiang Wang, Haichao Zhu, Pengjie Ren, Zhumin Chen, Dawei Yin, Maarten Rijke, and Zhaochun Ren. 2024. Learning to tokenize for generative retrieval. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599903"},{"key":"e_1_3_2_1_21_1","first-page":"21831","article-title":"Transformer memory as a differentiable search index","volume":"35","author":"Tay Yi","year":"2022","unstructured":"Yi Tay, Vinh Tran, Mostafa Dehghani, Jianmo Ni, Dara Bahri, Harsh Mehta, Zhen Qin, Kai Hui, Zhe Zhao, Jai Gupta, et al. 2022. Transformer memory as a differentiable search index. Advances in Neural Information Processing Systems 35 (2022), 21831--21843.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_22_1","volume-title":"Simlm: Pre-training with representation bottleneck for dense passage retrieval. arXiv preprint arXiv:2207.02578","author":"Wang Liang","year":"2022","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2022. Simlm: Pre-training with representation bottleneck for dense passage retrieval. arXiv preprint arXiv:2207.02578 (2022)."},{"key":"e_1_3_2_1_23_1","volume-title":"Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533","author":"Wang Liang","year":"2022","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2022. Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533 (2022)."},{"key":"e_1_3_2_1_24_1","first-page":"25600","article-title":"A neural corpus indexer for document retrieval","volume":"35","author":"Wang Yujing","year":"2022","unstructured":"Yujing Wang, Yingyan Hou, Haonan Wang, Ziming Miao, Shibin Wu, Qi Chen, Yuqing Xia, Chengmin Chi, Guoshuai Zhao, Zheng Liu, et al. 2022. A neural corpus indexer for document retrieval. Advances in Neural Information Processing Systems 35 (2022), 25600--25614.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614993"},{"key":"e_1_3_2_1_26_1","volume-title":"Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808","author":"Xiong Lee","year":"2020","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul Bennett, Junaid Ahmed, and Arnold Overwijk. 2020. Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808 (2020)."},{"key":"e_1_3_2_1_27_1","volume-title":"Term-Sets Can Be Strong Document Identifiers For Auto-Regressive Search Engines. arXiv preprint arXiv:2305.13859","author":"Zhang Peitian","year":"2023","unstructured":"Peitian Zhang, Zheng Liu, Yujia Zhou, Zhicheng Dou, and Zhao Cao. 2023. Term-Sets Can Be Strong Document Identifiers For Auto-Regressive Search Engines. arXiv preprint arXiv:2305.13859 (2023)."},{"key":"e_1_3_2_1_28_1","volume-title":"Ultron: An ultimate retriever on corpus with a model-based indexer. arXiv preprint arXiv:2208.09257","author":"Zhou Yujia","year":"2022","unstructured":"Yujia Zhou, Jing Yao, Zhicheng Dou, Ledell Wu, Peitian Zhang, and Ji-Rong Wen. 2022. Ultron: An ultimate retriever on corpus with a model-based indexer. arXiv preprint arXiv:2208.09257 (2022)."},{"key":"e_1_3_2_1_29_1","volume-title":"Bridging the gap between indexing and retrieval for differentiable search index with query generation. arXiv preprint arXiv:2206.10128","author":"Zhuang Shengyao","year":"2022","unstructured":"Shengyao Zhuang, Houxing Ren, Linjun Shou, Jian Pei, Ming Gong, Guido Zuccon, and Daxin Jiang. 2022. Bridging the gap between indexing and retrieval for differentiable search index with query generation. arXiv preprint arXiv:2206.10128 (2022)."}],"event":{"name":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Boise ID USA","acronym":"CIKM '24"},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679971","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3679971","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:16Z","timestamp":1750294696000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679971"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":29,"alternative-id":["10.1145\/3627673.3679971","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3679971","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}