{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:09:44Z","timestamp":1750219784697,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"CNPq"},{"name":"FAPEMIG"},{"name":"CAPES"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3592029","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:23Z","timestamp":1689726143000},"page":"2215-2219","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["On Answer Position Bias in Transformers for Question Answering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3828-492X","authenticated-orcid":false,"given":"Rafael","family":"Glater","sequence":"first","affiliation":[{"name":"Universidade Federal de Minas Gerais, Belo Horizonte, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2921-8444","authenticated-orcid":false,"given":"Rodrygo L. T.","family":"Santos","sequence":"additional","affiliation":[{"name":"Universidade Federal de Minas Gerais, Belo Horizonte, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_2_1_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_2_2_1","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00445"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5801"},{"key":"e_1_3_2_2_4_1","volume-title":"Deberta: Decoding-enhanced bert with disentangled attention. arXiv preprint arXiv:2006.03654","author":"He Pengcheng","year":"2020","unstructured":"Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2020. Deberta: Decoding-enhanced bert with disentangled attention. arXiv preprint arXiv:2006.03654 (2020)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-72113-8_16"},{"key":"e_1_3_2_2_6_1","volume-title":"Improve transformer models with better relative position embeddings. arXiv preprint arXiv:2009.13658","author":"Huang Zhiheng","year":"2020","unstructured":"Zhiheng Huang, Davis Liang, Peng Xu, and Bing Xiang. 2020. Improve transformer models with better relative position embeddings. arXiv preprint arXiv:2009.13658 (2020)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1356"},{"key":"e_1_3_2_2_8_1","volume-title":"Look at the first sentence: Position bias in question answering. arXiv preprint arXiv:2004.14602","author":"Ko Miyoung","year":"2020","unstructured":"Miyoung Ko, Jinhyuk Lee, Hyunjae Kim, Gangwoo Kim, and Jaewoo Kang. 2020. Look at the first sentence: Position bias in question answering. arXiv preprint arXiv:2004.14602 (2020)."},{"key":"e_1_3_2_2_9_1","volume-title":"Revealing the dark secrets of BERT. arXiv preprint arXiv:1908.08593","author":"Kovaleva Olga","year":"2019","unstructured":"Olga Kovaleva, Alexey Romanov, Anna Rogers, and Anna Rumshisky. 2019. Revealing the dark secrets of BERT. arXiv preprint arXiv:1908.08593 (2019)."},{"key":"e_1_3_2_2_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)."},{"key":"e_1_3_2_2_11_1","volume-title":"Yi Chern Tan, and Robert Frank","author":"Lin Yongjie","year":"2019","unstructured":"Yongjie Lin, Yi Chern Tan, and Robert Frank. 2019. Open Sesame: getting inside BERT's linguistic knowledge. arXiv preprint arXiv:1906.0169 (2019)."},{"key":"e_1_3_2_2_12_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)."},{"key":"e_1_3_2_2_13_1","volume-title":"International Conference on Machine Learning. PMLR, 7067--7079","author":"Liutkus Antoine","year":"2021","unstructured":"Antoine Liutkus, Ondvr ej C\u00edfka, Shih-Lun Wu, Umut Simsekli, Yi-Hsuan Yang, and Gael Richard. 2021. Relative positional encoding for transformers with linear complexity. In International Conference on Machine Learning. PMLR, 7067--7079."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1621"},{"key":"e_1_3_2_2_15_1","volume-title":"What do models learn from question answering datasets? arXiv preprint arXiv:2004.03490","author":"Sen Priyanka","year":"2020","unstructured":"Priyanka Sen and Amir Saffari. 2020. What do models learn from question answering datasets? arXiv preprint arXiv:2004.03490 (2020)."},{"key":"e_1_3_2_2_16_1","volume-title":"Self-attention with relative position representations. arXiv preprint arXiv:1803.02155","author":"Shaw Peter","year":"2018","unstructured":"Peter Shaw, Jakob Uszkoreit, and Ashish Vaswani. 2018. Self-attention with relative position representations. arXiv preprint arXiv:1803.02155 (2018)."},{"key":"e_1_3_2_2_17_1","first-page":"16857","article-title":"Mpnet: Masked and permuted pre-training for language understanding","volume":"33","author":"Song Kaitao","year":"2020","unstructured":"Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, and Tie-Yan Liu. 2020. Mpnet: Masked and permuted pre-training for language understanding. Advances in Neural Information Processing Systems, Vol. 33 (2020), 16857--16867.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_18_1","volume-title":"BERT rediscovers the classical NLP pipeline. arXiv preprint arXiv:1905.05950","author":"Tenney Ian","year":"2019","unstructured":"Ian Tenney, Dipanjan Das, and Ellie Pavlick. 2019. BERT rediscovers the classical NLP pipeline. arXiv preprint arXiv:1905.05950 (2019)."},{"key":"e_1_3_2_2_19_1","volume-title":"Attention is all you need. Advances in neural information processing systems","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. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_20_1","volume-title":"International Conference on Learning Representations.","author":"Wang Benyou","year":"2021","unstructured":"Benyou Wang, Lifeng Shang, Christina Lioma, Xin Jiang, Hao Yang, Qun Liu, and Jakob Grue Simonsen. 2021. On position embeddings in bert. In International Conference on Learning Representations."}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Taipei Taiwan","acronym":"SIGIR '23"},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3592029","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3592029","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:49Z","timestamp":1750178269000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3592029"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":20,"alternative-id":["10.1145\/3539618.3592029","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3592029","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}