{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T22:23:30Z","timestamp":1770330210207,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T00:00:00Z","timestamp":1677456000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,2,27]]},"DOI":"10.1145\/3539597.3570488","type":"proceedings-article","created":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T23:27:00Z","timestamp":1677108420000},"page":"1012-1020","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Beyond Hard Negatives in Product Search: Semantic Matching Using One-Class Classification (SMOCC)"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3492-7763","authenticated-orcid":false,"given":"Arindam","family":"Bhattacharya","sequence":"first","affiliation":[{"name":"Amazon, Bengaluru, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8286-2792","authenticated-orcid":false,"given":"Ankit","family":"Gandhi","sequence":"additional","affiliation":[{"name":"Amazon, Bengaluru, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7844-4379","authenticated-orcid":false,"given":"Vijay","family":"Huddar","sequence":"additional","affiliation":[{"name":"Amazon, Bengaluru, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3776-0607","authenticated-orcid":false,"given":"Ankith","family":"M S","sequence":"additional","affiliation":[{"name":"Amazon, Bengaluru, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3839-1978","authenticated-orcid":false,"given":"Aayush","family":"Moroney","sequence":"additional","affiliation":[{"name":"Amazon, Bengaluru, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0321-5069","authenticated-orcid":false,"given":"Atul","family":"Saroop","sequence":"additional","affiliation":[{"name":"Amazon, Bengaluru, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7187-4544","authenticated-orcid":false,"given":"Rahul","family":"Bhagat","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,2,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467440"},{"key":"e_1_3_2_2_2_1","volume-title":"Jiong Zhang, Kai Zhong, Kedarnath Kolluri, Qie Hu, Nikhil Shandilya, Vyacheslav Ievgrafov, Japinder Singh, and Inderjit S. Dhillon.","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, Japinder Singh, and Inderjit S. Dhillon. 2021. Extreme Multi-Label Learning for Semantic Matching in Product Search."},{"key":"e_1_3_2_2_3_1","volume-title":"ICML'20","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020b. A Simple Framework for Contrastive Learning of Visual Representations. In ICML'20."},{"key":"e_1_3_2_2_4_1","volume-title":"Improved Baselines with Momentum Contrastive Learning. arXiv preprint arXiv:2003.04297","author":"Chen Xinlei","year":"2020","unstructured":"Xinlei Chen, Haoqi Fan, Ross Girshick, and Kaiming He. 2020a. Improved Baselines with Momentum Contrastive Learning. arXiv preprint arXiv:2003.04297 (2020)."},{"key":"e_1_3_2_2_5_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, Minnesota, 4171--4186. https:\/\/www.aclweb.org\/anthology\/N19--1423"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330651"},{"key":"e_1_3_2_2_7_1","unstructured":"Tianyu Gao Xingcheng Yao and Danqi Chen. 2021. SimCSE: Simple Contrastive Learning of Sentence Embeddings."},{"key":"e_1_3_2_2_8_1","volume-title":"Dengel","author":"Goldstein Markus","year":"2012","unstructured":"Markus Goldstein and Andreas R. Dengel. 2012. Histogram-based Outlier Score (HBOS): A fast Unsupervised Anomaly Detection Algorithm."},{"key":"e_1_3_2_2_9_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning (PMLR '20)","author":"Goyal Sachin","year":"2020","unstructured":"Sachin Goyal, Aditi Raghunathan, Moksh Jain, Harsha Vardhan Simhadri, and Prateek Jain. 2020. DROCC: Deep Robust One-Class Classification. In Proceedings of the 37th International Conference on Machine Learning (PMLR '20). PMLR, Cambridge MA, USA, 3711--3721."},{"key":"e_1_3_2_2_10_1","unstructured":"Kaiming He Haoqi Fan Yuxin Wu Saining Xie and Ross Girshick. 2019. Momentum Contrast for Unsupervised Visual Representation Learning. https:\/\/arxiv.org\/abs\/1911.05722"},{"key":"e_1_3_2_2_11_1","volume-title":"Embedding-Based Retrieval in Facebook Search. In KDD '20","author":"Huang Jui-Ting","year":"2020","unstructured":"Jui-Ting Huang, Ashish Sharma, Shuying Sun, Li Xia, David Zhang, Philip Pronin, Janani Padmanabhan, Giuseppe Ottaviano, and Linjun Yang. 2020a. Embedding-Based Retrieval in Facebook Search. In KDD '20."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403305"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505665"},{"key":"e_1_3_2_2_14_1","volume-title":"Lin (Eds.)","volume":"33","author":"Kalantidis Yannis","year":"2020","unstructured":"Yannis Kalantidis, Mert Bulent Sariyildiz, Noe Pion, Philippe Weinzaepfel, and Diane Larlus. 2020. Hard Negative Mixing for Contrastive Learning. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 21798--21809. https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/f7cade80b7cc92b991cf4d2806d6bd78-Paper.pdf"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462926"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467149"},{"key":"e_1_3_2_2_17_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. arxiv","author":"Liu Yinhan","year":"1907","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: 1907.11692 [cs.CL]"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-industry.19"},{"key":"e_1_3_2_2_19_1","unstructured":"Aleksander Madry Aleksandar Makelov Ludwig Schmidt Dimitris Tsipras and Adrian Vladu. 2017. Towards Deep Learning Models Resistant to Adversarial Attacks."},{"key":"e_1_3_2_2_20_1","unstructured":"Yu. A. Malkov and D. A. Yashunin. 2018. Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs. arxiv: 1603.09320 [cs.DS]"},{"key":"e_1_3_2_2_21_1","unstructured":"Tomas Mikolov Kai Chen Greg Corrado and Jeffrey Dean. 2013. Efficient Estimation of Word Representations in Vector Space. arxiv: 1301.3781 [cs.CL]"},{"key":"e_1_3_2_2_22_1","volume-title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset.","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. (2016). https:\/\/www.microsoft.com\/en-us\/research\/publication\/ms-marco-human-generated-machine-reading-comprehension-dataset\/"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330759"},{"key":"e_1_3_2_2_24_1","volume-title":"OCGAN: One-Class Novelty Detection Using GANs With Constrained Latent Representations. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Perera Pramuditha","year":"2019","unstructured":"Pramuditha Perera, Ramesh Nallapati, and Bing Xiang. 2019. OCGAN: One-Class Novelty Detection Using GANs With Constrained Latent Representations. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019), 2893--2901."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-015-5521-0"},{"key":"e_1_3_2_2_26_1","unstructured":"Chandan K. Reddy Llu\u00eds M\u00e0rquez Fran Valero Nikhil Rao Hugo Zaragoza Sambaran Bandyopadhyay Arnab Biswas Anlu Xing and Karthik Subbian. 2022a. Shopping Queries Dataset: A Large-Scale ESCI Benchmark for Improving Product Search. arxiv: 2206.06588"},{"key":"e_1_3_2_2_27_1","unstructured":"Chandan K. Reddy Llu\u00eds M\u00e0rquez Fran Valero Nikhil Rao Hugo Zaragoza Sambaran Bandyopadhyay Arnab Biswas Anlu Xing and Karthik Subbian. 2022b. Shopping Queries Dataset: A Large-Scale ESCI Benchmark for Improving Product Search."},{"key":"e_1_3_2_2_28_1","volume-title":"Robert A. Vandermeulen, Alexander Binder, Emmanuel M\u00fcller, and M. Kloft.","author":"Ruff Lukas","year":"2018","unstructured":"Lukas Ruff, Nico G\u00f6rnitz, Lucas Deecke, Shoaib Ahmed Siddiqui, Robert A. Vandermeulen, Alexander Binder, Emmanuel M\u00fcller, and M. Kloft. 2018. Deep One-Class Classification. In ICML."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3052449"},{"key":"e_1_3_2_2_30_1","volume-title":"SIGIR","author":"Sourab Mangrulkar Ankith M S","year":"2022","unstructured":"Ankith M S, Sourab Mangrulkar, and Vivek Sembium. 2022. HISS: A novel hybrid inference architecture in embedding based product sourcing using knowledge distillation. In SIGIR 2022. https:\/\/www.amazon.science\/publications\/hiss-a-novel-hybrid-inference-architecture-in-embedding-based-product-sourcing-using-knowledge-distillation"},{"key":"e_1_3_2_2_31_1","volume-title":"Platt","author":"Sch\u00f6lkopf Bernhard","year":"1999","unstructured":"Bernhard Sch\u00f6lkopf, Robert C. Williamson, Alex Smola, John Shawe-Taylor, and John C. Platt. 1999. Support Vector Method for Novelty Detection. In NIPS."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"crossref","unstructured":"Yelong Shen Xiaodong He Jianfeng Gao Li Deng and Gregoire Mesnil. 2014. A Latent Semantic Model with Convolutional-Pooling Structure for Information Retrieval. In CIKM. https:\/\/www.microsoft.com\/en-us\/research\/publication\/a-latent-semantic-model-with-convolutional-pooling-structure-for-information-retrieval\/","DOI":"10.1145\/2661829.2661935"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:MACH.0000008084.60811.49"},{"key":"e_1_3_2_2_35_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention Is All You Need."},{"key":"e_1_3_2_2_36_1","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."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462880"},{"key":"e_1_3_2_2_39_1","volume-title":"Proceedings of the SIGIR 2019 Workshop on eCommerce (SIGIR 2019 eCom).","author":"Zhang Hongchun","year":"2019","unstructured":"Hongchun Zhang, Tianyi Wang, Xiaonan Meng, Yi Hu, and Hao Wang. 2019. Improving Semantic Matching via Multi-Task Learning in E-Commerce. In Proceedings of the SIGIR 2019 Workshop on eCommerce (SIGIR 2019 eCom)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21428"}],"event":{"name":"WSDM '23: The Sixteenth ACM International Conference on Web Search and Data Mining","location":"Singapore Singapore","acronym":"WSDM '23","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 Sixteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539597.3570488","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539597.3570488","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:15Z","timestamp":1750186935000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539597.3570488"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,27]]},"references-count":40,"alternative-id":["10.1145\/3539597.3570488","10.1145\/3539597"],"URL":"https:\/\/doi.org\/10.1145\/3539597.3570488","relation":{},"subject":[],"published":{"date-parts":[[2023,2,27]]},"assertion":[{"value":"2023-02-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}