{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T10:08:13Z","timestamp":1764842893700,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,25]],"date-time":"2023-10-25T00:00:00Z","timestamp":1698192000000},"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":[[2023,10,25]]},"DOI":"10.1145\/3639856.3639889","type":"proceedings-article","created":{"date-parts":[[2024,5,17]],"date-time":"2024-05-17T11:49:10Z","timestamp":1715946550000},"page":"1-5","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Noisy Text Data: foible of popular Transformer based NLP models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7204-1580","authenticated-orcid":false,"given":"Kartikay","family":"Bagla","sequence":"first","affiliation":[{"name":"Chaos Genius, IN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2052-4123","authenticated-orcid":false,"given":"Shivam","family":"Gupta","sequence":"additional","affiliation":[{"name":"Ninja Salary, IN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8742-5560","authenticated-orcid":false,"given":"Ankit","family":"Kumar","sequence":"additional","affiliation":[{"name":"Clearfeed, IN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7973-7089","authenticated-orcid":false,"given":"Anuj","family":"Gupta","sequence":"additional","affiliation":[{"name":"Gradient Advisors, IN"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,5,17]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_2_1_1_1","DOI":"10.1109\/ICDM.2007.21"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_2_1","DOI":"10.1016\/j.knosys.2019.105210"},{"key":"e_1_3_2_1_3_1","volume-title":"Stress test evaluation of transformer-based models in natural language understanding tasks. arXiv preprint arXiv:2002.06261","author":"Aspillaga Carlos","year":"2020","unstructured":"Carlos Aspillaga, Andr\u00e9s Carvallo, and Vladimir Araujo. 2020. Stress test evaluation of transformer-based models in natural language understanding tasks. arXiv preprint arXiv:2002.06261 (2020)."},{"key":"e_1_3_2_1_4_1","volume-title":"Synthetic and natural noise both break neural machine translation. arXiv preprint arXiv:1711.02173","author":"Belinkov Yonatan","year":"2017","unstructured":"Yonatan Belinkov and Yonatan Bisk. 2017. Synthetic and natural noise both break neural machine translation. arXiv preprint arXiv:1711.02173 (2017)."},{"key":"e_1_3_2_1_5_1","volume-title":"Semeval-2017 task 1: Semantic textual similarity-multilingual and cross-lingual focused evaluation. arXiv preprint arXiv:1708.00055","author":"Cer Daniel","year":"2017","unstructured":"Daniel Cer, Mona Diab, Eneko Agirre, Inigo Lopez-Gazpio, and Lucia Specia. 2017. Semeval-2017 task 1: Semantic textual similarity-multilingual and cross-lingual focused evaluation. arXiv preprint arXiv:1708.00055 (2017)."},{"key":"e_1_3_2_1_6_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_1_7_1","volume-title":"Is BERT Really Robust. A Strong Baseline for Natural Language Attack on Text Classification and Entailment","author":"Jin Di","year":"2019","unstructured":"Di Jin, Zhijing Jin, Joey\u00a0Tianyi Zhou, and Peter Szolovits. 2019. Is BERT Really Robust. A Strong Baseline for Natural Language Attack on Text Classification and Entailment (2019)."},{"key":"e_1_3_2_1_8_1","volume-title":"BillSum: A Corpus for Automatic Summarization of US Legislation. CoRR abs\/1910.00523","author":"Kornilova Anastassia","year":"2019","unstructured":"Anastassia Kornilova and Vlad Eidelman. 2019. BillSum: A Corpus for Automatic Summarization of US Legislation. CoRR abs\/1910.00523 (2019). arxiv:1910.00523http:\/\/arxiv.org\/abs\/1910.00523"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_9_1","DOI":"10.18653\/v1\/2020.wnut-1.3"},{"key":"e_1_3_2_1_10_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)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_11_1","DOI":"10.18653\/v1\/2021.wnut-1.45"},{"key":"e_1_3_2_1_12_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_13_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)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_14_1","DOI":"10.5555\/2002472.2002491"},{"key":"e_1_3_2_1_15_1","volume-title":"To Transfer or Not to Transfer: Misclassification Attacks Against Transfer Learned Text Classifiers. arXiv preprint arXiv:2001.02438","author":"Pal Bijeeta","year":"2020","unstructured":"Bijeeta Pal and Shruti Tople. 2020. To Transfer or Not to Transfer: Misclassification Attacks Against Transfer Learned Text Classifiers. arXiv preprint arXiv:2001.02438 (2020)."},{"key":"e_1_3_2_1_16_1","volume-title":"Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683","author":"Raffel Colin","year":"2019","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter\u00a0J Liu. 2019. Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683 (2019)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_17_1","DOI":"10.18653\/v1\/D16-1264"},{"key":"e_1_3_2_1_18_1","volume-title":"NoiseQA: Challenge Set Evaluation for User-Centric Question Answering. arXiv preprint arXiv:2102.08345","author":"Ravichander Abhilasha","year":"2021","unstructured":"Abhilasha Ravichander, Siddharth Dalmia, Maria Ryskina, Florian Metze, Eduard Hovy, and Alan\u00a0W Black. 2021. NoiseQA: Challenge Set Evaluation for User-Centric Question Answering. arXiv preprint arXiv:2102.08345 (2021)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_19_1","DOI":"10.18653\/v1\/P18-1079"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of Workshop on Text Summarization of ACL, Spain.","author":"CY","year":"2004","unstructured":"Lin\u00a0CY ROUGE. 2004. A package for automatic evaluation of summaries. In Proceedings of Workshop on Text Summarization of ACL, Spain."},{"key":"e_1_3_2_1_21_1","volume-title":"Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition. arXiv preprint cs\/0306050","author":"Sang F","year":"2003","unstructured":"Erik\u00a0F Sang and Fien De\u00a0Meulder. 2003. Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition. arXiv preprint cs\/0306050 (2003)."},{"key":"e_1_3_2_1_22_1","volume-title":"Bidirectional attention flow for machine comprehension. arXiv preprint arXiv:1611.01603","author":"Seo Minjoon","year":"2016","unstructured":"Minjoon Seo, Aniruddha Kembhavi, Ali Farhadi, and Hannaneh Hajishirzi. 2016. Bidirectional attention flow for machine comprehension. arXiv preprint arXiv:1611.01603 (2016)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_23_1","DOI":"10.18653\/v1\/D13-1170"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_24_1","DOI":"10.1145\/1568296.1568315"},{"key":"e_1_3_2_1_25_1","volume-title":"Adv-BERT: BERT is not robust on misspellings! Generating nature adversarial samples on BERT. ArXiv abs\/2003.04985","author":"Sun Lichao","year":"2020","unstructured":"Lichao Sun, Kazuma Hashimoto, Wenpeng Yin, Akari Asai, Jiugang Li, Philip\u00a0S. Yu, and Caiming Xiong. 2020. Adv-BERT: BERT is not robust on misspellings! Generating nature adversarial samples on BERT. ArXiv abs\/2003.04985 (2020)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_26_1","DOI":"10.1117\/12.410861"},{"unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998\u20136008.","key":"e_1_3_2_1_27_1"},{"key":"e_1_3_2_1_28_1","volume-title":"Machine comprehension using match-lstm and answer pointer. arXiv preprint arXiv:1608.07905","author":"Wang Shuohang","year":"2016","unstructured":"Shuohang Wang and Jing Jiang. 2016. Machine comprehension using match-lstm and answer pointer. arXiv preprint arXiv:1608.07905 (2016)."},{"key":"e_1_3_2_1_29_1","volume-title":"Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144","author":"Wu Yonghui","year":"2016","unstructured":"Yonghui Wu, Mike Schuster, Zhifeng Chen, Quoc\u00a0V Le, Mohammad Norouzi, Wolfgang Macherey, Maxim Krikun, Yuan Cao, Qin Gao, Klaus Macherey, 2016. Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144 (2016)."},{"key":"e_1_3_2_1_30_1","volume-title":"Xlnet: Generalized autoregressive pretraining for language understanding. Advances in neural information processing systems 32","author":"Yang Zhilin","year":"2019","unstructured":"Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Russ\u00a0R Salakhutdinov, and Quoc\u00a0V Le. 2019. Xlnet: Generalized autoregressive pretraining for language understanding. Advances in neural information processing systems 32 (2019)."}],"event":{"acronym":"AIMLSystems 2023","name":"AIMLSystems 2023: The Third International Conference on Artificial Intelligence and Machine Learning Systems","location":"Bangalore India"},"container-title":["The Third International Conference on Artificial Intelligence and Machine Learning Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3639856.3639889","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3639856.3639889","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T16:59:42Z","timestamp":1755881982000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3639856.3639889"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,25]]},"references-count":30,"alternative-id":["10.1145\/3639856.3639889","10.1145\/3639856"],"URL":"https:\/\/doi.org\/10.1145\/3639856.3639889","relation":{},"subject":[],"published":{"date-parts":[[2023,10,25]]},"assertion":[{"value":"2024-05-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}