{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:44:34Z","timestamp":1783737874152,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"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":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671654","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:55:12Z","timestamp":1724561712000},"page":"5339-5350","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Text Matching Indexers in Taobao Search"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2124-953X","authenticated-orcid":false,"given":"Sen","family":"Li","sequence":"first","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5918-093X","authenticated-orcid":false,"given":"Fuyu","family":"Lv","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4294-2541","authenticated-orcid":false,"given":"Ruqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"CAS Key Lab of Network Data Science and Technology, ICT, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9838-5343","authenticated-orcid":false,"given":"Dan","family":"Ou","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2397-1278","authenticated-orcid":false,"given":"Zhixuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1086-0202","authenticated-orcid":false,"given":"Maarten","family":"de Rijke","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Tensorflow: A System for Large-scale Machine Learning. In 12th OSDI. 265--283.","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al. 2016. Tensorflow: A System for Large-scale Machine Learning. In 12th OSDI. 265--283."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-7552(98)00110-X"},{"key":"e_1_3_2_1_3_1","volume-title":"12th CIKM. 426--434.","author":"Broder Andrei Z.","unstructured":"Andrei Z. Broder, David Carmel, Michael Herscovici, Aya Soffer, and Jason Zien. 2003. Efficient Query Evaluation Using a Two-level Retrieval Process. In 12th CIKM. 426--434."},{"key":"e_1_3_2_1_4_1","volume-title":"24th SIGIR. 43--50.","author":"Carmel David","unstructured":"David Carmel, Doron Cohen, Ronald Fagin, Eitan Farchi, Michael Herscovici, Yoelle S Maarek, and Aya Soffer. 2001. Static Index Pruning for Information Retrieval Systems. In 24th SIGIR. 43--50."},{"key":"e_1_3_2_1_5_1","volume-title":"Jiong Zhang, Kai Zhong, Kedarnath Kolluri, Qie Hu, Nikhil Shandilya, Vyacheslav Ievgrafov, et al.","author":"Chang Wei-Cheng","year":"2021","unstructured":"Wei-Cheng Chang, Daniel Jiang, Hsiang-Fu Yu, Choon Hui Teo, Jiong Zhang, Kai Zhong, Kedarnath Kolluri, Qie Hu, Nikhil Shandilya, Vyacheslav Ievgrafov, et al. 2021. Extreme Multi-label Learning for Semantic Matching in Product Search. In 27th SIGKDD. 2643--2651."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.19"},{"key":"e_1_3_2_1_7_1","volume-title":"IHGNN: Interactive Hypergraph Neural Network for Personalized Product Search. In 31st WWW. 256265.","author":"Cheng Dian","year":"2022","unstructured":"Dian Cheng, Jiawei Chen, Wenjun Peng, Wenqin Ye, Fuyu Lv, Tao Zhuang, Xiaoyi Zeng, and Xiangnan He. 2022. IHGNN: Interactive Hypergraph Neural Network for Personalized Product Search. In 31st WWW. 256265."},{"key":"e_1_3_2_1_8_1","volume-title":"43rd SIGIR. 1533--1536.","author":"Dai Zhuyun","unstructured":"Zhuyun Dai and Jamie Callan. 2020. Context-Aware Term Weighting For First Stage Passage Retrieval. In 43rd SIGIR. 1533--1536."},{"key":"e_1_3_2_1_9_1","volume-title":"Ng","author":"Dean Jeffrey","year":"2012","unstructured":"Jeffrey Dean, Greg S. Corrado, Rajat Monga, Kai Chen, Matthieu Devin, Quoc V. Le, Mark Z. Mao, Marc'Aurelio Ranzato, Andrew Senior, Paul Tucker, Ke Yang, and Andrew Y. Ng. 2012. Large Scale Distributed Deep Networks. In 25th NeurIPS. 1223--1231."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/1248547.1248548"},{"key":"e_1_3_2_1_11_1","volume-title":"34th SIGIR. 993--1002.","author":"Ding Shuai","unstructured":"Shuai Ding and Torsten Suel. 2011. Faster Top-k Document Retrieval Using Block-max Indexes. In 34th SIGIR. 993--1002."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2021068"},{"key":"e_1_3_2_1_13_1","volume-title":"31st WWW. 203--212.","author":"Fan Lu","unstructured":"Lu Fan, Qimai Li, Bo Liu, Xiao-Ming Wu, Xiaotong Zhang, Fuyu Lv, Guli Lin, Sen Li, Taiwei Jin, and Keping Yang. 2022. Modeling User Behavior with Graph Convolution for personalized product search. In 31st WWW. 203--212."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.14778\/3402755.3402756"},{"key":"e_1_3_2_1_15_1","volume-title":"45th SIGIR. 2353--2359.","author":"Formal Thibault","unstructured":"Thibault Formal, Carlos Lassance, Benjamin Piwowarski, and St\u00e9phane Clinchant. 2022. From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective. In 45th SIGIR. 2353--2359."},{"key":"e_1_3_2_1_16_1","volume-title":"SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking. In 44th SIGIR. 2288--2292.","author":"Formal Thibault","year":"2021","unstructured":"Thibault Formal, Benjamin Piwowarski, and St\u00e9phane Clinchant. 2021. SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking. In 44th SIGIR. 2288--2292."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3486250"},{"key":"e_1_3_2_1_18_1","volume-title":"26th SIGKDD. 2553--2561.","author":"Huang Jui-Ting","unstructured":"Jui-Ting Huang, Ashish Sharma, Shuying Sun, Li Xia, David Zhang, Philip Pronin, Janani Padmanabhan, Giuseppe Ottaviano, and Linjun Yang. 2020. Embedding-based Retrieval in Facebook Search. In 26th SIGKDD. 2553--2561."},{"key":"e_1_3_2_1_19_1","volume-title":"22nd CIKM. 2333--2338.","author":"Huang Po-Sen","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 Click through Data. In 22nd CIKM. 2333--2338."},{"key":"e_1_3_2_1_20_1","volume-title":"On Using Very Large Target Vocabulary for Neural Machine Translation. arXiv preprint arXiv:1412.2007","author":"Jean S\u00e9bastien","year":"2014","unstructured":"S\u00e9bastien Jean, Kyunghyun Cho, Roland Memisevic, and Yoshua Bengio. 2014. On Using Very Large Target Vocabulary for Neural Machine Translation. arXiv preprint arXiv:1412.2007 (2014)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_22_1","volume-title":"31st CIKM. 3262--3271.","author":"Li Sen","unstructured":"Sen Li, Fuyu Lv, Taiwei Jin, Guiyang Li, Yukun Zheng, Tao Zhuang, Qingwen Liu, Xiaoyi Zeng, James Kwok, and Qianli Ma. 2022. Query Rewriting in TaoBao Search. In 31st CIKM. 3262--3271."},{"key":"e_1_3_2_1_23_1","volume-title":"27th SIGKDD. 3181-3189.","author":"Li Sen","unstructured":"Sen Li, Fuyu Lv, Taiwei Jin, Guli Lin, Keping Yang, Xiaoyi Zeng, Xiao-Ming Wu, and Qianli Ma. 2021. Embedding-Based Product Retrieval in Taobao Search. In 27th SIGKDD. 3181-3189."},{"key":"e_1_3_2_1_24_1","volume-title":"27th SIGKDD. 3365--3375.","author":"Liu Yiding","unstructured":"Yiding Liu, Weixue Lu, Suqi Cheng, Daiting Shi, Shuaiqiang Wang, Zhicong Cheng, and Dawei Yin. 2021. Pre-trained Language Model for Web-scale Retrieval in Baidu Search. In 27th SIGKDD. 3365--3375."},{"key":"e_1_3_2_1_25_1","volume-title":"27th SIGKDD. 3376--3384.","author":"Liu Yiqun","unstructured":"Yiqun Liu, Kaushik Rangadurai, Yunzhong He, Siddarth Malreddy, Xunlong Gui, Xiaoyi Liu, and Fedor Borisyuk. 2021. Que2Search: Fast and Accurate Query and Document Understanding for Search at Facebook. In 27th SIGKDD. 3376--3384."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-012722442-8\/50020-3"},{"key":"e_1_3_2_1_27_1","volume-title":"27th SIGKDD. 3385--3393.","author":"Luo Xusheng","unstructured":"Xusheng Luo, Le Bo, Jinhang Wu, Lin Li, Zhiy Luo, Yonghua Yang, and Keping Yang. 2021. AliCoCo2: Commonsense Knowledge Extraction, Representation and Application in E-commerce. In 27th SIGKDD. 3385--3393."},{"key":"e_1_3_2_1_28_1","volume-title":"Wacky Weights in Learned Sparse Representations and the Revenge of Score-at-a-Time Query Evaluation. arXiv preprint arXiv:2110.11540","author":"Mackenzie Joel","year":"2021","unstructured":"Joel Mackenzie, Andrew Trotman, and Jimmy Lin. 2021. Wacky Weights in Learned Sparse Representations and the Revenge of Score-at-a-Time Query Evaluation. arXiv preprint arXiv:2110.11540 (2021)."},{"key":"e_1_3_2_1_29_1","article-title":"Efficient Document-at-a-Time and Score-at-a-Time Query Evaluation for Learned Sparse Representations","volume":"41","author":"Mackenzie Joel","year":"2023","unstructured":"Joel Mackenzie, Andrew Trotman, and Jimmy Lin. 2023. Efficient Document-at-a-Time and Score-at-a-Time Query Evaluation for Learned Sparse Representations. ACM Transactions on Information Systems 41, 4 (2023).","journal-title":"ACM Transactions on Information Systems"},{"key":"e_1_3_2_1_30_1","volume-title":"Ajit Puthenputhussery, Sijie Chen, Min Xie, Anirudh Kashi, Tony Lee, et al.","author":"Magnani Alessandro","year":"2022","unstructured":"Alessandro Magnani, Feng Liu, Suthee Chaidaroon, Sachin Yadav, Praveen Reddy Suram, Ajit Puthenputhussery, Sijie Chen, Min Xie, Anirudh Kashi, Tony Lee, et al. 2022. Semantic Retrieval at Walmart. In 28th SIGKDD. 3495--3503."},{"key":"e_1_3_2_1_31_1","volume-title":"44th SIGIR. 17231727.","author":"Mallia Antonio","unstructured":"Antonio Mallia, Omar Khattab, Torsten Suel, and Nicola Tonellotto. 2021. Learning Passage Impacts for Inverted Indexes. In 44th SIGIR. 17231727."},{"key":"e_1_3_2_1_32_1","volume-title":"Hao Gu, and Bing Yin.","author":"Nigam Priyanka","year":"2019","unstructured":"Priyanka Nigam, Yiwei Song, Vijai Mohan, Vihan Lakshman, Weitian Ding, Ankit Shingavi, Choon Hui Teo, Hao Gu, and Bing Yin. 2019. Semantic Product Search. In 25th SIGKDD. 2876--2885."},{"key":"e_1_3_2_1_33_1","volume-title":"26th SIGKDD. 3405--3415.","author":"Niu Xichuan","unstructured":"Xichuan Niu, Bofang Li, Chenliang Li, Rong Xiao, Haochuan Sun, Hongbo Deng, and Zhenzhong Chen. 2020. A Dual Heterogeneous Graph Attention Network to Improve Long-Tail Performance for Shop Search in E-Commerce. In 26th SIGKDD. 3405--3415."},{"key":"e_1_3_2_1_34_1","volume-title":"30th SIGIR. 191--198.","author":"Ntoulas Alexandros","unstructured":"Alexandros Ntoulas and Junghoo Cho. 2007. Pruning Policies for Two-Tiered Inverted Index with Correctness Guarantee. In 30th SIGIR. 191--198."},{"key":"e_1_3_2_1_35_1","volume-title":"6th WSDM. 73--82.","author":"Panigrahi Debmalya","unstructured":"Debmalya Panigrahi and Sreenivas Gollapudi. 2013. Document Selection for Tiered Indexing in Commerce Search. In 6th WSDM. 73--82."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsif.2014.0378"},{"key":"e_1_3_2_1_37_1","unstructured":"Joseph Rocchio. 1971. Relevance Feedback in Information Retrieval. In The Smart Retrieval System-experiments in Automatic Document Processing. 313--323."},{"key":"e_1_3_2_1_38_1","volume-title":"da Silva","author":"Rossi Cristian","year":"2013","unstructured":"Cristian Rossi, Edleno S. de Moura, Andre L. Carvalho, and Altigran S. da Silva. 2013. Fast Document-at-a-time Query Processing Using Two-tier Indexes. In 36th SIGIR. 183--192."},{"key":"e_1_3_2_1_39_1","volume-title":"Introduction to Information Retrieval","author":"Sch\u00fctze Hinrich","unstructured":"Hinrich Sch\u00fctze, Christopher D. Manning, and Prabhakar Raghavan. 2008. Introduction to Information Retrieval. Vol. 39. Cambridge University Press."},{"key":"e_1_3_2_1_40_1","volume-title":"23rd WWW. 373--374.","author":"Shen Yelong","unstructured":"Yelong Shen, Xiaodong He, Jianfeng Gao, Li Deng, and Gr\u00e9goire Mesnil. 2014. Learning Semantic Representations Using Convolutional Neural Networks for Web Search. In 23rd WWW. 373--374."},{"key":"e_1_3_2_1_41_1","volume-title":"28th SIGIR. 219--225.","author":"Strohman Trevor","unstructured":"Trevor Strohman, Howard Turtle, and W. Bruce Croft. 2005. Optimization Strategies for Complex Queries. In 28th SIGIR. 219--225."},{"key":"e_1_3_2_1_42_1","volume-title":"Ernie: Enhanced Representation Through Knowledge Integration. arXiv preprint arXiv:1904.09223","author":"Sun Yu","year":"2019","unstructured":"Yu Sun, Shuohuan Wang, Yukun Li, Shikun Feng, Xuyi Chen, Han Zhang, Xin Tian, Danxiang Zhu, Hao Tian, and Hua Wu. 2019. Ernie: Enhanced Representation Through Knowledge Integration. arXiv preprint arXiv:1904.09223 (2019)."},{"key":"e_1_3_2_1_43_1","volume-title":"BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track.","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/0306-4573(95)00020-H"},{"key":"e_1_3_2_1_45_1","volume-title":"31st NeurIPS","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All You Need. In 31st NeurIPS, Vol. 30."},{"key":"e_1_3_2_1_46_1","volume-title":"30th WWW. 2890--2899.","author":"Yao Shaowei","unstructured":"Shaowei Yao, Jiwei Tan, Xi Chen, Keping Yang, Rong Xiao, Hongbo Deng, and Xiaojun Wan. 2021. Learning a Product Relevance Model from Click-Through Data in E-Commerce. In 30th WWW. 2890--2899."},{"key":"e_1_3_2_1_47_1","volume-title":"28th SIGKDD, pages=4433-4442","author":"Yu Licheng","year":"2022","unstructured":"Licheng Yu, Jun Chen, Animesh Sinha, Mengjiao Wang, Yu Chen, Tamara L Berg, and Ning Zhang. [n. d.]. CommerceMM: Large-scale Commerce Multimodal Representation Learning with Omni Retrieval. In 28th SIGKDD, pages=4433-4442, year=2022."},{"key":"e_1_3_2_1_48_1","volume-title":"44th SIGIR. ACM, 17181722.","author":"Zhang Han","unstructured":"Han Zhang, Hongwei Shen, Yiming Qiu, Yunjiang Jiang, Songlin Wang, Sulong Xu, Yun Xiao, Bo Long, and Wen-Yun Yang. 2021. Joint Learning of Deep Retrieval Model and Product Quantization based Embedding Index. In 44th SIGIR. ACM, 17181722."},{"key":"e_1_3_2_1_49_1","volume-title":"43rd SIGIR. 2407--2416.","author":"Zhang Han","unstructured":"Han Zhang, Songlin Wang, Kang Zhang, Zhiling Tang, Yunjiang Jiang, Yun Xiao, Weipeng Yan, and Wen-Yun Yang. 2020. Towards Personalized and Semantic Retrieval: An End-to-End Solution for E-commerce Search via Embedding Learning. In 43rd SIGIR. 2407--2416."},{"key":"e_1_3_2_1_50_1","volume-title":"SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval. arXiv preprint arXiv:2009.13013","author":"Zhao Tiancheng","year":"2020","unstructured":"Tiancheng Zhao, Xiaopeng Lu, and Kyusong Lee. 2020. SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval. arXiv preprint arXiv:2009.13013 (2020)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/1132956.1132959"}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain","acronym":"KDD '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671654","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671654","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:06:00Z","timestamp":1750291560000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671654"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":51,"alternative-id":["10.1145\/3637528.3671654","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671654","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}