{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T19:50:18Z","timestamp":1773690618791,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,2,11]],"date-time":"2022-02-11T00:00:00Z","timestamp":1644537600000},"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":[[2022,2,11]]},"DOI":"10.1145\/3488560.3498442","type":"proceedings-article","created":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T21:42:57Z","timestamp":1644961377000},"page":"1275-1283","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Fast Semantic Matching via Flexible Contextualized Interaction"],"prefix":"10.1145","author":[{"given":"Wenwen","family":"Ye","sequence":"first","affiliation":[{"name":"Baidu Inc., Beijing, China"}]},{"given":"Yiding","family":"Liu","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]},{"given":"Lixin","family":"Zou","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]},{"given":"Hengyi","family":"Cai","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}]},{"given":"Suqi","family":"Cheng","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]},{"given":"Shuaiqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]},{"given":"Dawei","family":"Yin","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2022,2,15]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Longformer: The longdocument transformer. arXiv preprint arXiv:2004.05150","author":"Beltagy Iz","year":"2020","unstructured":"Iz Beltagy, Matthew E Peters, and Arman Cohan. 2020. Longformer: The longdocument transformer. arXiv preprint arXiv:2004.05150 (2020)."},{"key":"e_1_3_2_2_2_1","volume-title":"Reading wikipedia to answer open-domain questions. arXiv preprint arXiv:1704.00051","author":"Chen Danqi","year":"2017","unstructured":"Danqi Chen, Adam Fisch, Jason Weston, and Antoine Bordes. 2017. Reading wikipedia to answer open-domain questions. arXiv preprint arXiv:1704.00051 (2017)."},{"key":"e_1_3_2_2_3_1","volume-title":"Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509","author":"Child Rewon","year":"2019","unstructured":"Rewon Child, Scott Gray, Alec Radford, and Ilya Sutskever. 2019. Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509 (2019)."},{"key":"e_1_3_2_2_4_1","volume-title":"visualising and summarising documents with a single convolutional neural network. arXiv preprint arXiv:1406.3830","author":"Denil Misha","year":"2014","unstructured":"Misha Denil, Alban Demiraj, Nal Kalchbrenner, Phil Blunsom, and Nando de Freitas. 2014. Modelling, visualising and summarising documents with a single convolutional neural network. arXiv preprint arXiv:1406.3830 (2014)."},{"key":"e_1_3_2_2_5_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","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. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_2_6_1","volume-title":"Searchqa: A new q&a dataset augmented with context from a search engine. arXiv preprint arXiv:1704.05179","author":"Dunn Matthew","year":"2017","unstructured":"Matthew Dunn, Levent Sagun, Mike Higgins, V Ugur Guney, Volkan Cirik, and Kyunghyun Cho. 2017. Searchqa: A new q&a dataset augmented with context from a search engine. arXiv preprint arXiv:1704.05179 (2017)."},{"key":"e_1_3_2_2_7_1","volume-title":"Pre-training Methods in Information Retrieval. arXiv preprint arXiv:2111.13853","author":"Fan Yixing","year":"2021","unstructured":"Yixing Fan, Xiaohui Xie, Yinqiong Cai, Jia Chen, Xinyu Ma, Xiangsheng Li, Ruqing Zhang, Jiafeng Guo, and Yiqun Liu. 2021. Pre-training Methods in Information Retrieval. arXiv preprint arXiv:2111.13853 (2021)."},{"key":"e_1_3_2_2_8_1","volume-title":"Axial Attention in Multidimensional Transformers. arXiv preprint arXiv:1912.12180","author":"Ho Jonathan","year":"2019","unstructured":"Jonathan Ho, Nal Kalchbrenner, DirkWeissenborn, and Tim Salimans. 2019. Axial Attention in Multidimensional Transformers. arXiv preprint arXiv:1912.12180 (2019)."},{"key":"e_1_3_2_2_9_1","unstructured":"Baotian Hu Zhengdong Lu Hang Li and Qingcai Chen. 2014. Convolutional neural network architectures for matching natural language sentences. In NeurIPS. 2042--2050."},{"key":"e_1_3_2_2_10_1","volume-title":"Parameterized convolutional neural networks for aspect level sentiment classification. arXiv preprint arXiv:1909.06276","author":"Huang Binxuan","year":"2019","unstructured":"Binxuan Huang and KathleenMCarley. 2019. Parameterized convolutional neural networks for aspect level sentiment classification. arXiv preprint arXiv:1909.06276 (2019)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"crossref","unstructured":"Jui-Ting Huang Ashish Sharma Shuying Sun Li Xia David Zhang Philip Pronin Janani Padmanabhan Giuseppe Ottaviano and Linjun Yang. 2020. Embeddingbased Retrieval in Facebook Search. In SIGKDD. 2553--2561.","DOI":"10.1145\/3394486.3403305"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"crossref","unstructured":"Po-Sen Huang Xiaodong He Jianfeng Gao Li Deng Alex Acero and Larry Heck. 2013. Learning deep structured semantic models for web search using clickthrough data. In CIKM. 2333--2338.","DOI":"10.1145\/2505515.2505665"},{"key":"e_1_3_2_2_13_1","volume-title":"Pacrr: A position-aware neural ir model for relevance matching. arXiv preprint arXiv:1704.03940","author":"Hui Kai","year":"2017","unstructured":"Kai Hui, Andrew Yates, Klaus Berberich, and Gerard de Melo. 2017. Pacrr: A position-aware neural ir model for relevance matching. arXiv preprint arXiv:1704.03940 (2017)."},{"key":"e_1_3_2_2_14_1","volume-title":"Poly-encoders: Transformer architectures and pre-training strategies for fast and accurate multi-sentence scoring. arXiv preprint arXiv:1905.01969","author":"Humeau Samuel","year":"2019","unstructured":"Samuel Humeau, Kurt Shuster, Marie-Anne Lachaux, and Jason Weston. 2019. Poly-encoders: Transformer architectures and pre-training strategies for fast and accurate multi-sentence scoring. arXiv preprint arXiv:1905.01969 (2019)."},{"key":"e_1_3_2_2_15_1","volume-title":"Transformers are rnns: Fast autoregressive transformers with linear attention. arXiv preprint arXiv:2006.16236","author":"Katharopoulos Angelos","year":"2020","unstructured":"Angelos Katharopoulos, Apoorv Vyas, Nikolaos Pappas, and Fran\u00e7ois Fleuret. 2020. Transformers are rnns: Fast autoregressive transformers with linear attention. arXiv preprint arXiv:2006.16236 (2020)."},{"key":"e_1_3_2_2_16_1","volume-title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT. arXiv preprint arXiv:2004.12832","author":"Khattab Omar","year":"2020","unstructured":"Omar Khattab and Matei Zaharia. 2020. ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT. arXiv preprint arXiv:2004.12832 (2020)."},{"key":"e_1_3_2_2_17_1","volume-title":"Reformer: The efficient transformer. arXiv preprint arXiv:2001.04451","author":"Kitaev Nikita","year":"2020","unstructured":"Nikita Kitaev, Anselm Levskaya. 2020. Reformer: The efficient transformer. arXiv preprint arXiv:2001.04451 (2020)."},{"key":"e_1_3_2_2_18_1","volume-title":"Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942","author":"Lan Zhenzhong","year":"2019","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2019. Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942 (2019)."},{"key":"e_1_3_2_2_19_1","unstructured":"Juho Lee Yoonho Lee Jungtaek Kim Adam Kosiorek Seungjin Choi and Yee Whye Teh. 2019. Set transformer: A framework for attention-based permutation-invariant neural networks. In ICML. PMLR 3744--3753."},{"key":"e_1_3_2_2_20_1","volume-title":"Latent retrieval for weakly supervised open domain question answering. arXiv preprint arXiv:1906.00300","author":"Lee Kenton","year":"2019","unstructured":"Kenton Lee, Ming-Wei Chang, and Kristina Toutanova. 2019. Latent retrieval for weakly supervised open domain question answering. arXiv preprint arXiv:1906.00300 (2019)."},{"key":"e_1_3_2_2_21_1","volume-title":"Generating wikipedia by summarizing long sequences. arXiv preprint arXiv:1801.10198","author":"Liu Peter J","year":"2018","unstructured":"Peter J Liu, Mohammad Saleh, Etienne Pot, Ben Goodrich, Ryan Sepassi, Lukasz Kaiser, and Noam Shazeer. 2018. Generating wikipedia by summarizing long sequences. arXiv preprint arXiv:1801.10198 (2018)."},{"key":"e_1_3_2_2_22_1","volume-title":"Multitask deep neural networks for natural language understanding. arXiv preprint arXiv:1901.11504","author":"Liu Xiaodong","year":"2019","unstructured":"Xiaodong Liu, Pengcheng He, Weizhu Chen, and Jianfeng Gao. 2019. Multitask deep neural networks for natural language understanding. arXiv preprint arXiv:1901.11504 (2019)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"crossref","unstructured":"Yiding Liu Weixue Lu Suqi Cheng Daiting Shi Shuaiqiang Wang Zhicong Cheng and Dawei Yin. 2021. Pre-Trained Language Model forWeb-Scale Retrieval in Baidu Search. In SIGKDD. 3365--3375.","DOI":"10.1145\/3447548.3467149"},{"key":"e_1_3_2_2_24_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_2_25_1","volume-title":"The ubuntu dialogue corpus: A large dataset for research in unstructured multi-turn dialogue systems. arXiv preprint arXiv:1506.08909","author":"Lowe Ryan","year":"2015","unstructured":"Ryan Lowe, Nissan Pow, Iulian Serban, and Joelle Pineau. 2015. The ubuntu dialogue corpus: A large dataset for research in unstructured multi-turn dialogue systems. arXiv preprint arXiv:1506.08909 (2015)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"Jonas Mueller and Aditya Thyagarajan. 2016. Siamese recurrent architectures for learning sentence similarity. In AAAI.","DOI":"10.1609\/aaai.v30i1.10350"},{"key":"e_1_3_2_2_27_1","volume-title":"MS MARCO: A human generated machine reading comprehension dataset. In CoCo@NIPS.","author":"Nguyen Tri","year":"2016","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. In CoCo@NIPS."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"Ping Nie Yuyu Zhang Xiubo Geng Arun Ramamurthy Le Song and Daxin Jiang. 2020. DC-BERT: Decoupling Question and Document for Efficient Contextual Encoding. In SIGIR. 1829--1832.","DOI":"10.1145\/3397271.3401271"},{"key":"e_1_3_2_2_29_1","volume-title":"Image transformer. arXiv preprint arXiv:1802.05751","author":"Parmar Niki","year":"2018","unstructured":"Niki Parmar, Ashish Vaswani, Jakob Uszkoreit, Lukasz Kaiser, Noam Shazeer, Alexander Ku, and Dustin Tran. 2018. Image transformer. arXiv preprint arXiv:1802.05751 (2018)."},{"key":"e_1_3_2_2_30_1","volume-title":"OpenAI","author":"Radford Alec","year":"2018","unstructured":"Alec Radford, Karthik Narasimhan, Tim Salimans, and Ilya Sutskever. 2018. Improving language understanding with unsupervised learning. Technical report, OpenAI (2018)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"crossref","unstructured":"Corby Rosset Damien Jose Gargi Ghosh Bhaskar Mitra and Saurabh Tiwary. 2018. Optimizing query evaluations using reinforcement learning for web search. In SIGIR. 1193--1196.","DOI":"10.1145\/3209978.3210127"},{"key":"e_1_3_2_2_32_1","volume-title":"Efficient content-based sparse attention with routing transformers. arXiv preprint arXiv:2003.05997","author":"Roy Aurko","year":"2020","unstructured":"Aurko Roy, Mohammad Saffar, Ashish Vaswani, and David Grangier. 2020. Efficient content-based sparse attention with routing transformers. arXiv preprint arXiv:2003.05997 (2020)."},{"key":"e_1_3_2_2_33_1","unstructured":"Kihyuk Sohn. 2016. Improved deep metric learning with multi-class n-pair loss objective. In NeurIPS. 1857--1865."},{"key":"e_1_3_2_2_34_1","volume-title":"Sparse Sinkhorn Attention. arXiv preprint arXiv:2002.11296","author":"Tay Yi","year":"2020","unstructured":"Yi Tay, Dara Bahri, Liu Yang, Donald Metzler, and Da-Cheng Juan. 2020. Sparse Sinkhorn Attention. arXiv preprint arXiv:2002.11296 (2020)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.3934\/mbe.2020055"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Chenyan Xiong Zhuyun Dai Jamie Callan Zhiyuan Liu and Russell Power. 2017. End-to-end neural ad-hoc ranking with kernel pooling. In SIGIR. 55--64.","DOI":"10.1145\/3077136.3080809"},{"key":"e_1_3_2_2_37_1","volume-title":"Xlnet: Generalized autoregressive pretraining for language understanding. In NeurIPS. 5753--5763.","author":"Yang Zhilin","year":"2019","unstructured":"Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Russ R Salakhutdinov, and Quoc V Le. 2019. Xlnet: Generalized autoregressive pretraining for language understanding. In NeurIPS. 5753--5763."},{"key":"e_1_3_2_2_38_1","volume-title":"Hotpotqa: A dataset for diverse, explainable multi-hop question answering. arXiv preprint arXiv:1809.09600","author":"Yang Zhilin","year":"2018","unstructured":"Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, WilliamWCohen, Ruslan Salakhutdinov, and Christopher D Manning. 2018. Hotpotqa: A dataset for diverse, explainable multi-hop question answering. arXiv preprint arXiv:1809.09600 (2018)."},{"key":"e_1_3_2_2_39_1","volume-title":"Lazaros Polymenakos, Chulaka Gunasekara, Walter S Lasecki, Jonathan K Kummerfeld, Michel Galley, Chris Brockett, et al.","author":"Yoshino Koichiro","year":"2019","unstructured":"Koichiro Yoshino, Chiori Hori, Julien Perez, Luis Fernando D'Haro, Lazaros Polymenakos, Chulaka Gunasekara, Walter S Lasecki, Jonathan K Kummerfeld, Michel Galley, Chris Brockett, et al. 2019. Dialog system technology challenge 7. arXiv preprint arXiv:1901.03461 (2019)."},{"key":"e_1_3_2_2_40_1","unstructured":"Manzil Zaheer Guru Guruganesh Avinava Dubey Joshua Ainslie Chris Alberti Santiago Ontanon Philip Pham Anirudh Ravula QifanWang Li Yang et al. 2020. Big bird: Transformers for longer sequences. arXiv preprint arXiv:2007.14062 (2020)."},{"key":"e_1_3_2_2_41_1","volume-title":"DC-BERT: Decoupling Question and Document for Efficient Contextual Encoding. arXiv preprint arXiv:2002.12591","author":"Zhang Yuyu","year":"2020","unstructured":"Yuyu Zhang, Ping Nie, Xiubo Geng, Arun Ramamurthy, Le Song, and Daxin Jiang. 2020. DC-BERT: Decoupling Question and Document for Efficient Contextual Encoding. arXiv preprint arXiv:2002.12591 (2020)."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.10.030"},{"key":"e_1_3_2_2_43_1","volume-title":"ERNIE: Enhanced language representation with informative entities. arXiv preprint arXiv:1905.07129","author":"Zhang Zhengyan","year":"2019","unstructured":"Zhengyan Zhang, Xu Han, Zhiyuan Liu, Xin Jiang, Maosong Sun, and Qun Liu. 2019. ERNIE: Enhanced language representation with informative entities. arXiv preprint arXiv:1905.07129 (2019)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00368"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"crossref","unstructured":"Lixin Zou Shengqiang Zhang Hengyi Cai Dehong Ma Suqi Cheng Shuaiqiang Wang Daiting Shi Zhicong Cheng and Dawei Yin. 2021. Pre-trained language model based ranking in Baidu search. In SIGKDD. 4014--4022.","DOI":"10.1145\/3447548.3467147"}],"event":{"name":"WSDM '22: The Fifteenth ACM International Conference on Web Search and Data Mining","location":"Virtual Event AZ USA","acronym":"WSDM '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3488560.3498442","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3488560.3498442","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:31:18Z","timestamp":1750188678000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3488560.3498442"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,11]]},"references-count":45,"alternative-id":["10.1145\/3488560.3498442","10.1145\/3488560"],"URL":"https:\/\/doi.org\/10.1145\/3488560.3498442","relation":{},"subject":[],"published":{"date-parts":[[2022,2,11]]},"assertion":[{"value":"2022-02-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}