{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/pre-training-transformer-models-with-sentence","title":"Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection","arxiv_id":"2205.10455","date":"2022-05-20","proceeding":null,"authors":["Luca Di Liello","Siddhant Garg","Luca Soldaini","Alessandro Moschitti"],"abstract":"An important task for designing QA systems is answer sentence selection (AS2): selecting the sentence containing (or constituting) the answer to a question from a set of retrieved relevant documents. In this paper, we propose three novel sentence-level transformer pre-training objectives that incorporate paragraph-level semantics within and across documents, to improve the performance of transformers for AS2, and mitigate the requirement of large labeled datasets. Specifically, the model is tasked to predict whether: (i) two sentences are extracted from the same paragraph, (ii) a given sentence is extracted from a given paragraph, and (iii) two paragraphs are extracted from the same document. Our experiments on three public and one industrial AS2 datasets demonstrate the empirical superiority of our pre-trained transformers over baseline models such as RoBERTa and ELECTRA for AS2.","url_abs":"https://arxiv.org/abs/2205.10455v2","url_pdf":"https://arxiv.org/pdf/2205.10455v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"answer-selection","task_name":"Answer Selection"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"electra","method_name":"ELECTRA"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"roberta","method_name":"RoBERTa"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/answer-selection-on-asnq","task":"Answer Selection","dataset":"ASNQ","model":"DeBERTa-V3-Large + SSP","rank_in_archive_order":1,"of":3,"metrics":{"MAP":"0.743","MRR":"0.800"},"uses_additional_data":false},{"leaderboard":"/sota/answer-selection-on-asnq","task":"Answer Selection","dataset":"ASNQ","model":"ELECTRA-Base + SSP","rank_in_archive_order":2,"of":3,"metrics":{"MAP":"0.697","MRR":"0.757"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-trecqa","task":"Question Answering","dataset":"TrecQA","model":"DeBERTa-V3-Large + SSP","rank_in_archive_order":3,"of":13,"metrics":{"MAP":"0.923","MRR":"0.946"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-trecqa","task":"Question Answering","dataset":"TrecQA","model":"RoBERTa-Base + PSD","rank_in_archive_order":7,"of":13,"metrics":{"MAP":"0.903","MRR":"0.951"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-wikiqa","task":"Question Answering","dataset":"WikiQA","model":"DeBERTa-V3-Large + ALL","rank_in_archive_order":4,"of":25,"metrics":{"MAP":"0.909","MRR":"0.920"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-wikiqa","task":"Question Answering","dataset":"WikiQA","model":"DeBERTa-Large + SSP","rank_in_archive_order":5,"of":25,"metrics":{"MAP":"0.901","MRR":"0.914"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-wikiqa","task":"Question Answering","dataset":"WikiQA","model":"RoBERTa-Base + SSP","rank_in_archive_order":7,"of":25,"metrics":{"MAP":"0.887","MRR":"0.899"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.10455","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}