{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:02:40Z","timestamp":1750309360874,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":28,"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\/3637528.3671625","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:55:12Z","timestamp":1724561712000},"page":"4928-4938","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing E-commerce Spelling Correction with Fine-Tuned Transformer Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4515-5294","authenticated-orcid":false,"given":"Arnab","family":"Dutta","sequence":"first","affiliation":[{"name":"eBay GmbH, Dreilinden, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6407-7341","authenticated-orcid":false,"given":"Gleb","family":"Polushin","sequence":"additional","affiliation":[{"name":"eBay GmbH, Dreilinden, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1861-8233","authenticated-orcid":false,"given":"Xiaoshuang","family":"Zhang","sequence":"additional","affiliation":[{"name":"eBay Inc., Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7285-8788","authenticated-orcid":false,"given":"Daniel","family":"Stein","sequence":"additional","affiliation":[{"name":"eBay GmbH, Aachen, Germany"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"NAACL 2019, 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations). 54--59","author":"Akbik Alan","year":"2019","unstructured":"Alan Akbik, Tanja Bergmann, Duncan Blythe, Kashif Rasul, Stefan Schweter, and Roland Vollgraf. 2019. FLAIR: An easy-to-use framework for state-of-the-art NLP. In NAACL 2019, 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations). 54--59."},{"key":"e_1_3_2_2_2_1","unstructured":"Kevin Atkinson. 2019. GNU Aspell."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383200"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICS51289.2020.00113"},{"key":"e_1_3_2_2_5_1","unstructured":"Hyung Won Chung Le Hou Shayne Longpre Barret Zoph Yi Tay William Fedus Eric Li Xuezhi Wang Mostafa Dehghani Siddhartha Brahma et al. 2022. Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)."},{"key":"e_1_3_2_2_6_1","unstructured":"ONNX Runtime developers. 2021. ONNX Runtime. https:\/\/onnxruntime.ai\/. Version: x.y.z."},{"key":"e_1_3_2_2_7_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arxiv","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. arxiv: 1810.04805 [cs.CL]"},{"key":"e_1_3_2_2_8_1","volume-title":"Hierarchical character tagger for short text spelling error correction. arXiv preprint arXiv:2109.14259","author":"Gao Mengyi","year":"2021","unstructured":"Mengyi Gao, Canran Xu, and Peng Shi. 2021. Hierarchical character tagger for short text spelling error correction. arXiv preprint arXiv:2109.14259 (2021)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSC.2020.00023"},{"key":"e_1_3_2_2_10_1","unstructured":"Chengming Hu Xuan Li Dan Liu Xi Chen Ju Wang and Xue Liu. 2022. Teacher-Student Architecture for Knowledge Learning: A Survey. arxiv: 2210.17332 [cs.LG]"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_12_1","unstructured":"Lu Jingwen Long Jidong and Majumder Rangan. 2021. Speller100: Zero-shot spelling correction at scale for 100-plus languages. https:\/\/www.microsoft.com\/en-us\/research\/blog\/speller100-zero-shot-spelling-correction-at-scale-for-100-plus-languages\/"},{"key":"e_1_3_2_2_13_1","volume-title":"COLING 1990","volume":"2036","author":"Kernighan Mark D.","unstructured":"Mark D. Kernighan, Kenneth W. Church, and William A. Gale. 1990. A Spelling Correction Program Based on a Noisy Channel Model. In COLING 1990 Volume 2: Papers presented to the 13th International Conference on Computational Linguistics. https:\/\/aclanthology.org\/C90--2036"},{"key":"e_1_3_2_2_14_1","volume-title":"Rush","author":"Kim Yoon","year":"2015","unstructured":"Yoon Kim, Yacine Jernite, David Sontag, and Alexander M. Rush. 2015. Character-Aware Neural Language Models. arxiv: 1508.06615 [cs.CL]"},{"key":"e_1_3_2_2_15_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_2_16_1","volume-title":"Spelling Error Correction Using a Nested RNN Model and Pseudo Training Data. arxiv","author":"Li Hao","year":"1811","unstructured":"Hao Li, Yang Wang, Xinyu Liu, Zhichao Sheng, and Si Wei. 2018. Spelling Error Correction Using a Nested RNN Model and Pseudo Training Data. arxiv: 1811.00238 [cs.CL]"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00343"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2037"},{"key":"e_1_3_2_2_19_1","unstructured":"Filipp Ozinov. 2019. Jamspell."},{"key":"e_1_3_2_2_20_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","year":"1912","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas K\u00f6pf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. arxiv: 1912.01703 [cs.LG]"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455856"},{"key":"e_1_3_2_2_23_1","unstructured":"Sascha Rothe Jonathan Mallinson Eric Malmi Sebastian Krause and Aliaksei Severyn. 2022. A Simple Recipe for Multilingual Grammatical Error Correction. arxiv: 2106.03830 [cs.CL]"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASERT.2019.8934902"},{"key":"e_1_3_2_2_25_1","volume-title":"Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications. Association for Computational Linguistics, Online, 37--47","author":"Stahlberg Felix","year":"2021","unstructured":"Felix Stahlberg and Shankar Kumar. 2021. Synthetic Data Generation for Grammatical Error Correction with Tagged Corruption Models. In Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications. Association for Computational Linguistics, Online, 37--47. https:\/\/aclanthology.org\/2021.bea-1.4"},{"key":"e_1_3_2_2_26_1","volume-title":"Chi, Quoc Le, and Denny Zhou","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed Chi, Quoc Le, and Denny Zhou. 2022. Chain of thought prompting elicits reasoning in large language models. arXiv preprint arXiv:2201.11903 (2022)."},{"key":"e_1_3_2_2_27_1","volume-title":"mT5: A massively multilingual pre-trained text-to-text transformer. arxiv","author":"Xue Linting","year":"2010","unstructured":"Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, and Colin Raffel. 2021. mT5: A massively multilingual pre-trained text-to-text transformer. arxiv: 2010.11934 [cs.CL]"},{"key":"e_1_3_2_2_28_1","volume-title":"Yifei Teng, Yan Gao, Jia Liu, Jingyuan Deng, and Yi Sun.","author":"Yang Fan","year":"2022","unstructured":"Fan Yang, Ali Bagheri Garakani, Yifei Teng, Yan Gao, Jia Liu, Jingyuan Deng, and Yi Sun. 2022. Spelling correction using phonetics in e-commerce search. (2022)."}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Barcelona Spain","acronym":"KDD '24"},"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\/3637528.3671625","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671625","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:05:59Z","timestamp":1750291559000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671625"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":28,"alternative-id":["10.1145\/3637528.3671625","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671625","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"}}]}}