{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T03:50:48Z","timestamp":1770349848440,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T00:00:00Z","timestamp":1691107200000},"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":[[2023,8,6]]},"DOI":"10.1145\/3580305.3599402","type":"proceedings-article","created":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T18:10:58Z","timestamp":1691172658000},"page":"36-46","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["LEA: Improving Sentence Similarity Robustness to Typos Using Lexical Attention Bias"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4339-2959","authenticated-orcid":false,"given":"Mario","family":"Almagro","sequence":"first","affiliation":[{"name":"NielsenIQ Innovation, Madrid, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1583-3749","authenticated-orcid":false,"given":"Emilio","family":"Almaz\u00e1n","sequence":"additional","affiliation":[{"name":"NielsenIQ Innovation, Madrid, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1011-3610","authenticated-orcid":false,"given":"Diego","family":"Ortego","sequence":"additional","affiliation":[{"name":"NielsenIQ Innovation, Madrid, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7194-5541","authenticated-orcid":false,"given":"David","family":"Jim\u00e9nez","sequence":"additional","affiliation":[{"name":"NielsenIQ Innovation, Madrid, Spain"}]}],"member":"320","published-online":{"date-parts":[[2023,8,4]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2018. GPT-2 HuggingFace. https:\/\/huggingface.co\/docs\/transformers\/model_doc\/gpt2.  2018. GPT-2 HuggingFace. https:\/\/huggingface.co\/docs\/transformers\/model_doc\/gpt2."},{"key":"e_1_3_2_2_2_1","unstructured":"2020. GPT-Neo HuggingFace. https:\/\/huggingface.co\/EleutherAI\/gpt-neo-1.3B.  2020. GPT-Neo HuggingFace. https:\/\/huggingface.co\/EleutherAI\/gpt-neo-1.3B."},{"key":"e_1_3_2_2_3_1","unstructured":"M. Almagro D. Jim\u00e9nez D. Ortego E. Almaz\u00e1n and E. Mart\u00ednez. 2020. Block-SCL: Blocking Matters for Supervised Contrastive Learning in Product Matching. In International ACM SIGIR conference on research and development in Information Retrieval (SIGIR) Workshop on e-commerce.  M. Almagro D. Jim\u00e9nez D. Ortego E. Almaz\u00e1n and E. Mart\u00ednez. 2020. Block-SCL: Blocking Matters for Supervised Contrastive Learning in Product Matching. In International ACM SIGIR conference on research and development in Information Retrieval (SIGIR) Workshop on e-commerce."},{"key":"e_1_3_2_2_4_1","volume-title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. arXiv:1611.09268","author":"Bajaj P.","year":"2016","unstructured":"P. Bajaj , D. Campos , N. Craswell , L. Deng , J. Gao , X. Liu , R. Majumder , A. Mc- Namara , B. Mitra , T. Nguyen , M. Rosenberg , X. Song , S. Tiwary A. Stoica , and T. Wang . 2016 . MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. arXiv:1611.09268 (2016). P. Bajaj, D. Campos, N. Craswell, L. Deng, J. Gao, X. Liu, R. Majumder, A. Mc- Namara, B. Mitra, T. Nguyen, M. Rosenberg, X. Song, S. Tiwary A. Stoica, and T. Wang. 2016. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. arXiv:1611.09268 (2016)."},{"key":"e_1_3_2_2_5_1","volume":"202","author":"Chuang Y.-S.","unstructured":"Y.-S. Chuang , R. Dangovski , H. Luo , Y. Zhang , S. Chang , M. Solja?i?, S.-W. Li , W. Yih , Y. Kim , and J. Glass. 202 2. DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings. (2022). Y.-S. Chuang, R. Dangovski, H. Luo, Y. Zhang, S. Chang, M. Solja?i?, S.-W. Li, W. Yih, Y. Kim, and J. Glass. 2022. DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings. (2022).","journal-title":"J. Glass."},{"key":"e_1_3_2_2_6_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Clark K.","unstructured":"K. Clark , M.-T. Luong , Q.V. Le , and C.D. Manning . 2020. ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators . In International Conference on Learning Representations (ICLR). K. Clark, M.-T. Luong, Q.V. Le, and C.D. Manning. 2020. ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_7_1","volume-title":"Pairwise Supervised Contrastive Learning of Sentence Representations. In Conference on Empirical Methods in Natural Language Processing (EMNLP).","author":"Zhang W. Xiao H.","year":"2021","unstructured":"W. Xiao H. Zhu R. Nallapati A.O. Arnold B. Xiang D. Zhang , S.-W. Li . 2021 . Pairwise Supervised Contrastive Learning of Sentence Representations. In Conference on Empirical Methods in Natural Language Processing (EMNLP). W. Xiao H. Zhu R. Nallapati A.O. Arnold B. Xiang D. Zhang, S.-W. Li. 2021. Pairwise Supervised Contrastive Learning of Sentence Representations. In Conference on Empirical Methods in Natural Language Processing (EMNLP)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"crossref","unstructured":"Z. Dai Z. Yang Y. Yang J.G. Carbonell Q.V. Le and R. Salakhutdinov. 2019. Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context. arXiv:1901.02860 (2019).  Z. Dai Z. Yang Y. Yang J.G. Carbonell Q.V. Le and R. Salakhutdinov. 2019. Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context. arXiv:1901.02860 (2019).","DOI":"10.18653\/v1\/P19-1285"},{"key":"e_1_3_2_2_9_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Conference of the North American Chapter of the Association for Computational Linguistics (NAACL).","author":"Devlin J.","unstructured":"J. Devlin , M.-W. Chang , K. Lee , and K. Toutanova . 2019 . BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Conference of the North American Chapter of the Association for Computational Linguistics (NAACL). J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"crossref","unstructured":"N. Gali R. Mariescu-Istodor D. Hostettler and P. Fr\u00e4nti. 2019. Framework for syntactic string similarity measures. Expert Systems with Applications (2019).  N. Gali R. Mariescu-Istodor D. Hostettler and P. Fr\u00e4nti. 2019. Framework for syntactic string similarity measures. Expert Systems with Applications (2019).","DOI":"10.1016\/j.eswa.2019.03.048"},{"key":"e_1_3_2_2_11_1","volume-title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings. In Conference on Empirical Methods in Natural Language Processing (EMNLP).","author":"Gao T.","unstructured":"T. Gao , X. Yao , and D. Chen . 2021 . SimCSE: Simple Contrastive Learning of Sentence Embeddings. In Conference on Empirical Methods in Natural Language Processing (EMNLP). T. Gao, X. Yao, and D. Chen. 2021. SimCSE: Simple Contrastive Learning of Sentence Embeddings. In Conference on Empirical Methods in Natural Language Processing (EMNLP)."},{"key":"e_1_3_2_2_12_1","volume-title":"Self-Attention Attribution: Interpreting Information Interactions Inside Transformer. In AAAI Conference on Artificial Intelligence.","author":"Hao Y.","unstructured":"Y. Hao , L. Dong , F. Wei , and K. Xu . 2021 . Self-Attention Attribution: Interpreting Information Interactions Inside Transformer. In AAAI Conference on Artificial Intelligence. Y. Hao, L. Dong, F. Wei, and K. Xu. 2021. Self-Attention Attribution: Interpreting Information Interactions Inside Transformer. In AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_2_13_1","volume-title":"AAAI Conference on Artificial Intelligence.","author":"Hong T.","unstructured":"T. Hong , D. Kim , M. Ji , W. Hwang , D. Nam , and S. Park . 2022. Bros: A pre-trained language model focusing on text and layout for better key information extraction from documents . In AAAI Conference on Artificial Intelligence. T. Hong, D. Kim, M. Ji,W. Hwang, D. Nam, and S. Park. 2022. Bros: A pre-trained language model focusing on text and layout for better key information extraction from documents. In AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_2_14_1","volume":"202","author":"Humeau S.","unstructured":"S. Humeau , K. Shuster , M.-A. Lachaux , and J. Weston. 202 0. Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring. In International Conference on Learning Representations (ICLR). S. Humeau, K. Shuster, M.-A. Lachaux, and J. Weston. 2020. Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring. In International Conference on Learning Representations (ICLR).","journal-title":"J. Weston."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5506"},{"key":"e_1_3_2_2_16_1","volume-title":"Baleen: Robust multi-hop reasoning at scale via condensed retrieval. In Advances in Neural Information Processing Systems (NeurIPS).","author":"Khattab O.","year":"2021","unstructured":"O. Khattab , C. Potts , and M. Zaharia . 2021 . Baleen: Robust multi-hop reasoning at scale via condensed retrieval. In Advances in Neural Information Processing Systems (NeurIPS). O. Khattab, C. Potts, and M. Zaharia. 2021. Baleen: Robust multi-hop reasoning at scale via condensed retrieval. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_2_17_1","volume-title":"International ACM SIGIR conference on research and development in Information Retrieval (SIGIR).","author":"Khattab O.","unstructured":"O. Khattab and M. Zaharia . 2020. Colbert: Efficient and effective passage search via contextualized late interaction over bert . In International ACM SIGIR conference on research and development in Information Retrieval (SIGIR). O. Khattab and M. Zaharia. 2020. Colbert: Efficient and effective passage search via contextualized late interaction over bert. In International ACM SIGIR conference on research and development in Information Retrieval (SIGIR)."},{"key":"e_1_3_2_2_18_1","unstructured":"P. Khosla P. Teterwak C. Wang A. Sarna Y. Tian P. Isola A. Maschinot C. Liu and D. Krishnan. 2021. Supervised Contrastive Learning. In Advances in Neural Information Processing Systems (NeurIPS).  P. Khosla P. Teterwak C. Wang A. Sarna Y. Tian P. Isola A. Maschinot C. Liu and D. Krishnan. 2021. Supervised Contrastive Learning. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_2_19_1","volume-title":"PARADE: Passage Representation Aggregation for Document Reranking. arXiv:2008.09093","author":"Li C.","year":"2020","unstructured":"C. Li , A. Yates , S. MacAvaney , B. He , and Y. Sun . 2020 . PARADE: Passage Representation Aggregation for Document Reranking. arXiv:2008.09093 (2020). C. Li, A. Yates, S. MacAvaney, B. He, and Y. Sun. 2020. PARADE: Passage Representation Aggregation for Document Reranking. arXiv:2008.09093 (2020)."},{"key":"e_1_3_2_2_20_1","volume-title":"Deep Entity Matching with Pre-Trained Language Models. In International Conference on Very Large Data Bases (VLDB).","author":"Li Y","year":"2020","unstructured":"Y Li , J. Li , Y. Suhara , A. Doan , and W.-C. Tan . 2020 . Deep Entity Matching with Pre-Trained Language Models. In International Conference on Very Large Data Bases (VLDB). Y Li, J. Li, Y. Suhara, A. Doan, and W.-C. Tan. 2020. Deep Entity Matching with Pre-Trained Language Models. In International Conference on Very Large Data Bases (VLDB)."},{"key":"e_1_3_2_2_21_1","volume-title":"CAPE: Encoding relative positions with continuous augmented positional embeddings. Advances in Neural Information Processing Systems (NeurIPS)","author":"Likhomanenko T.","year":"2021","unstructured":"T. Likhomanenko , Q. Xu , G. Synnaeve , Ronan Collobert , and Alex Rogozhnikov . 2021 . CAPE: Encoding relative positions with continuous augmented positional embeddings. Advances in Neural Information Processing Systems (NeurIPS) (2021). T. Likhomanenko, Q. Xu, G. Synnaeve, Ronan Collobert, and Alex Rogozhnikov. 2021. CAPE: Encoding relative positions with continuous augmented positional embeddings. Advances in Neural Information Processing Systems (NeurIPS) (2021)."},{"key":"e_1_3_2_2_22_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Liu F.","unstructured":"F. Liu , Y. Jiao , J. Massiah , E. Yilmaz , and S. Havrylov . 2021. Trans-Encoder: Unsupervised sentence-pair modelling through self-and mutual-distillations . In International Conference on Learning Representations (ICLR). F. Liu, Y. Jiao, J. Massiah, E. Yilmaz, and S. Havrylov. 2021. Trans-Encoder: Unsupervised sentence-pair modelling through self-and mutual-distillations. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_23_1","volume-title":"Pre-Trained Language Model for Web-Scale Retrieval in Baidu Search. In ACM SIGKDD Conference on Knowledge Discovery & Data Mining (KDD).","author":"Liu Y.","unstructured":"Y. Liu , W. Lu , S. Cheng , D. Shi , S. Wang , Z. Cheng , and D. Yin . 2021 . Pre-Trained Language Model for Web-Scale Retrieval in Baidu Search. In ACM SIGKDD Conference on Knowledge Discovery & Data Mining (KDD). Y. Liu, W. Lu, S. Cheng, D. Shi, S. Wang, Z. Cheng, and D. Yin. 2021. Pre-Trained Language Model for Web-Scale Retrieval in Baidu Search. In ACM SIGKDD Conference on Knowledge Discovery & Data Mining (KDD)."},{"key":"e_1_3_2_2_24_1","volume-title":"Conference on Empirical Methods in Natural Language Processing (EMNLP).","author":"Moradi M.","unstructured":"M. Moradi and M. Samwald . 2021. Evaluating the Robustness of Neural Language Models to Input Perturbations . In Conference on Empirical Methods in Natural Language Processing (EMNLP). M. Moradi and M. Samwald. 2021. Evaluating the Robustness of Neural Language Models to Input Perturbations. In Conference on Empirical Methods in Natural Language Processing (EMNLP)."},{"key":"e_1_3_2_2_25_1","volume-title":"Deep Learning for Entity Matching: A Design Space Exploration. In ACM International Conference on Management of Data (ICDM).","author":"Mudgal S.","unstructured":"S. Mudgal , H. Li , T. Rekatsinas , A. Doan , Y. Park , G. Krishnan , R. Deep , E. Arcaute , and V. Raghavendra . 2018 . Deep Learning for Entity Matching: A Design Space Exploration. In ACM International Conference on Management of Data (ICDM). S. Mudgal, H. Li, T. Rekatsinas, A. Doan, Y. Park, G. Krishnan, R. Deep, E. Arcaute, and V. Raghavendra. 2018. Deep Learning for Entity Matching: A Design Space Exploration. In ACM International Conference on Management of Data (ICDM)."},{"key":"e_1_3_2_2_26_1","volume-title":"SGPT: GPT Sentence Embeddings for Semantic Search. arXiv:2202.08904","author":"Muennighoff N.","year":"2022","unstructured":"N. Muennighoff . 2022 . SGPT: GPT Sentence Embeddings for Semantic Search. arXiv:2202.08904 (2022). N. Muennighoff. 2022. SGPT: GPT Sentence Embeddings for Semantic Search. arXiv:2202.08904 (2022)."},{"key":"e_1_3_2_2_27_1","unstructured":"R. Nogueira and K. Cho. 2019. Passage Re-ranking with BERT. arXiv:1901.04085 (2019).  R. Nogueira and K. Cho. 2019. Passage Re-ranking with BERT. arXiv:1901.04085 (2019)."},{"key":"e_1_3_2_2_28_1","volume-title":"Conference and Labs of the Evaluation Forum (CLEF).","author":"Passaro L.C.","unstructured":"L.C. Passaro , A. Bondielli , A. Lenci , and F. Marcelloni . 2020. UNIPI-NLE at Check- That! 2020: Approaching Fact Checking from a Sentence Similarity Perspective Through the Lens of Transformers . In Conference and Labs of the Evaluation Forum (CLEF). L.C. Passaro, A. Bondielli, A. Lenci, and F. Marcelloni. 2020. UNIPI-NLE at Check- That! 2020: Approaching Fact Checking from a Sentence Similarity Perspective Through the Lens of Transformers. In Conference and Labs of the Evaluation Forum (CLEF)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"crossref","unstructured":"R. Peeters and C. Bizer. 2022. Supervised Contrastive Learning for Product Matching. arXiv: 2202.02098 (2022).  R. Peeters and C. Bizer. 2022. Supervised Contrastive Learning for Product Matching. arXiv: 2202.02098 (2022).","DOI":"10.1145\/3487553.3524254"},{"key":"e_1_3_2_2_30_1","volume-title":"Test Long: Attention with Linear Biases Enables Input Length Extrapolation. In International Conference on Learning Representations (ICLR).","author":"Press O.","unstructured":"O. Press , N. Smith , and M. Lewis . 2022. Train Short , Test Long: Attention with Linear Biases Enables Input Length Extrapolation. In International Conference on Learning Representations (ICLR). O. Press, N. Smith, and M. Lewis. 2022. Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_31_1","volume-title":"The WDC Training Dataset and Gold Standard for Large-Scale Product Matching. In World Wide Web Conference (WWWC).","author":"Primpeli A.","unstructured":"A. Primpeli , R. Peeters , and C. Bizer . 2019 . The WDC Training Dataset and Gold Standard for Large-Scale Product Matching. In World Wide Web Conference (WWWC). A. Primpeli, R. Peeters, and C. Bizer. 2019. The WDC Training Dataset and Gold Standard for Large-Scale Product Matching. In World Wide Web Conference (WWWC)."},{"key":"e_1_3_2_2_32_1","volume-title":"Combating Adversarial Misspellings with Robust Word Recognition. In Annual Meeting of the Association for Computational Linguistics (ACL).","author":"Pruthi D.","unstructured":"D. Pruthi , B. Dhingra , and Z.C. Lipton . 2019 . Combating Adversarial Misspellings with Robust Word Recognition. In Annual Meeting of the Association for Computational Linguistics (ACL). D. Pruthi, B. Dhingra, and Z.C. Lipton. 2019. Combating Adversarial Misspellings with Robust Word Recognition. In Annual Meeting of the Association for Computational Linguistics (ACL)."},{"key":"e_1_3_2_2_33_1","volume-title":"ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (BCB).","author":"Liu Majid R.-M., S.","unstructured":"Majid R.-M., S. Liu , Y. Wang , N. Afzal , L. Wang , F. Shen , S. Fu , and H. Liu . 2018. BioCreative\/OHNLP Challenge 2018 . In ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (BCB). Majid R.-M., S. Liu, Y. Wang, N. Afzal, L. Wang, F. Shen, S. Fu, and H. Liu. 2018. BioCreative\/OHNLP Challenge 2018. In ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (BCB)."},{"key":"e_1_3_2_2_34_1","volume":"202","author":"Raffel C.","unstructured":"C. Raffel , N. Shazeer , A. Roberts , K. Lee , S. Narang , M. Matena , Y. Zhou , W. Li , and P. J. Liu. 202 0. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research (JMLR) (2020). C. Raffel, N. Shazeer, A. Roberts, K. Lee, S. Narang, M. Matena, Y. Zhou,W. Li, and P.J. Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research (JMLR) (2020).","journal-title":"J. Liu."},{"key":"e_1_3_2_2_35_1","volume-title":"Conference on Empirical Methods in Natural Language Processing and International Joint Conference on Natural Language Processing (EMNLP-IJCNLP).","author":"Reimers N.","unstructured":"N. Reimers and I. Gurevych . 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks . In Conference on Empirical Methods in Natural Language Processing and International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). N. Reimers and I. Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. In Conference on Empirical Methods in Natural Language Processing and International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)."},{"key":"e_1_3_2_2_36_1","unstructured":"G. Rosa L. Bonifacio V. Jeronymo H. Abonizio M. Fadaee R. Lotufo and R. Nogueira. 2022. In Defense of Cross-Encoders for Zero-Shot Retrieval. arXiv:2212.06121 (2022).  G. Rosa L. Bonifacio V. Jeronymo H. Abonizio M. Fadaee R. Lotufo and R. Nogueira. 2022. In Defense of Cross-Encoders for Zero-Shot Retrieval. arXiv:2212.06121 (2022)."},{"key":"e_1_3_2_2_37_1","volume-title":"Conference of the North American Chapter of the Association for Computational Linguistics (NAACL).","author":"Santhanam K.","unstructured":"K. Santhanam , O. Khattab , J. Saad-Falcon , C. Potts , and M. Zaharia . 2022. Colbertv2: Effective and efficient retrieval via lightweight late interaction . In Conference of the North American Chapter of the Association for Computational Linguistics (NAACL). K. Santhanam, O. Khattab, J. Saad-Falcon, C. Potts, and M. Zaharia. 2022. Colbertv2: Effective and efficient retrieval via lightweight late interaction. In Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)."},{"key":"e_1_3_2_2_38_1","volume-title":"Self-Attention with Relative Position Representations. In Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): Human Language Technologies.","author":"Shaw P.","unstructured":"P. Shaw , J. Uszkoreit , and A. Vaswani . 2018 . Self-Attention with Relative Position Representations. In Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): Human Language Technologies. P. Shaw, J. Uszkoreit, and A. Vaswani. 2018. Self-Attention with Relative Position Representations. In Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): Human Language Technologies."},{"key":"e_1_3_2_2_39_1","volume-title":"Analysing the Robustness of Dual Encoders for Dense Retrieval Against Misspellings. In International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR).","author":"Sidiropoulos G.","unstructured":"G. Sidiropoulos and E. Kanoulas . 2022 . Analysing the Robustness of Dual Encoders for Dense Retrieval Against Misspellings. In International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR). G. Sidiropoulos and E. Kanoulas. 2022. Analysing the Robustness of Dual Encoders for Dense Retrieval Against Misspellings. In International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)."},{"key":"e_1_3_2_2_40_1","unstructured":"L. Sun K. Hashimoto W. Yin A. Asai J. Li P. Yu and C. Xiong. 2020. Adv-BERT: BERT is not robust on misspellings! Generating nature adversarial samples on BERT. arXiv:2003.04985 (2020).  L. Sun K. Hashimoto W. Yin A. Asai J. Li P. Yu and C. Xiong. 2020. Adv-BERT: BERT is not robust on misspellings! Generating nature adversarial samples on BERT. arXiv:2003.04985 (2020)."},{"key":"e_1_3_2_2_41_1","volume-title":"EcomNLP Workshop.","author":"Tracz J.","unstructured":"J. Tracz , P.I. W\u00f3jcik , K. Jasinska-Kobus , R. Belluzzo , R. Mroczkowski , and I. Gawlik . 2020. BERT-based similarity learning for product matching. In Association for Computational Linguistics (ACL) , EcomNLP Workshop. J. Tracz, P.I. W\u00f3jcik, K. Jasinska-Kobus, R. Belluzzo, R. Mroczkowski, and I. Gawlik. 2020. BERT-based similarity learning for product matching. In Association for Computational Linguistics (ACL), EcomNLP Workshop."},{"key":"e_1_3_2_2_42_1","unstructured":"I. Turc M.-W. Chang K. Lee and K. Toutanova. 2019. Well-Read Students Learn Better: On the Importance of Pre-training Compact Models. arXiv:1908.08962 (2019).  I. Turc M.-W. Chang K. Lee and K. Toutanova. 2019. Well-Read Students Learn Better: On the Importance of Pre-training Compact Models. arXiv:1908.08962 (2019)."},{"key":"e_1_3_2_2_43_1","unstructured":"A. Vaswani N. Shazeer N. Parmar J. Uszkoreit L. Jones A.N. Gomez L. Kaiser and I. Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems (NeurIPS) (2017).  A. Vaswani N. Shazeer N. Parmar J. Uszkoreit L. Jones A.N. Gomez L. Kaiser and I. Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems (NeurIPS) (2017)."},{"key":"e_1_3_2_2_44_1","volume-title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding. In International Conference on Learning Representations (ICLR).","author":"Wang A.","unstructured":"A. Wang , Amanpreet Singh , Julian Michael , F. Hill , O. Levy , and S. Bowman . 2018 . GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding. In International Conference on Learning Representations (ICLR). A.Wang, Amanpreet Singh, Julian Michael, F. Hill, O. Levy, and S. Bowman. 2018. GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"crossref","unstructured":"U. Wennberg and G.E. Henter. 2021. The Case for Translation-Invariant Self- Attention in Transformer-Based Language Models. In Annual Meeting of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing (ACL-IJCNLP).  U. Wennberg and G.E. Henter. 2021. The Case for Translation-Invariant Self- Attention in Transformer-Based Language Models. In Annual Meeting of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing (ACL-IJCNLP).","DOI":"10.18653\/v1\/2021.acl-short.18"},{"key":"e_1_3_2_2_46_1","volume-title":"DA-Transformer: Distance-aware Transformer. In Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): Human Language Technologies.","author":"Wu C.","unstructured":"C. Wu , F. Wu , and Y. Huang . 2021 . DA-Transformer: Distance-aware Transformer. In Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): Human Language Technologies. C.Wu, F.Wu, and Y. Huang. 2021. DA-Transformer: Distance-aware Transformer. In Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): Human Language Technologies."},{"key":"e_1_3_2_2_47_1","volume-title":"Annual Meeting of the Association for Computational Linguistics (ACL).","author":"Yang J.","unstructured":"J. Yang , A. Gupta , S. Upadhyay , L. He , R. Goel , and S. Paul . 2022. Tableformer: Robust transformer modeling for table-text encoding . In Annual Meeting of the Association for Computational Linguistics (ACL). J. Yang, A. Gupta, S. Upadhyay, L. He, R. Goel, and S. Paul. 2022. Tableformer: Robust transformer modeling for table-text encoding. In Annual Meeting of the Association for Computational Linguistics (ACL)."},{"key":"e_1_3_2_2_48_1","volume-title":"Dealing with Typos for BERT-based Passage Retrieval and Ranking. In Conference on Empirical Methods in Natural Language Processing (EMNLP).","author":"Zhuang S.","unstructured":"S. Zhuang and G. Zuccon . 2021 . Dealing with Typos for BERT-based Passage Retrieval and Ranking. In Conference on Empirical Methods in Natural Language Processing (EMNLP). S. Zhuang and G. Zuccon. 2021. Dealing with Typos for BERT-based Passage Retrieval and Ranking. In Conference on Empirical Methods in Natural Language Processing (EMNLP)."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"crossref","unstructured":"S. Zhuang and G. Zuccon. 2022. CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos. In International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR).  S. Zhuang and G. Zuccon. 2022. CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos. In International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR).","DOI":"10.1145\/3477495.3531951"},{"key":"e_1_3_2_2_50_1","volume-title":"Conference on Empirical Methods in Natural Language Processing (EMNLP).","author":"Zhuang S.","unstructured":"S. Zhuang and G. Zuccon . 2022. VIRT: Improving Representation-based Models for Text Matching through Virtual Interaction . In Conference on Empirical Methods in Natural Language Processing (EMNLP). S. Zhuang and G. Zuccon. 2022. VIRT: Improving Representation-based Models for Text Matching through Virtual Interaction. In Conference on Empirical Methods in Natural Language Processing (EMNLP)."}],"event":{"name":"KDD '23: The 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Long Beach CA USA","acronym":"KDD '23","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 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599402","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3580305.3599402","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:36Z","timestamp":1750178256000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599402"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,4]]},"references-count":50,"alternative-id":["10.1145\/3580305.3599402","10.1145\/3580305"],"URL":"https:\/\/doi.org\/10.1145\/3580305.3599402","relation":{},"subject":[],"published":{"date-parts":[[2023,8,4]]},"assertion":[{"value":"2023-08-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}