Papers › Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection

Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection

20 May 2022arXiv:2205.10455archive 2025-07-28

Luca Di Liello, Siddhant Garg, Luca Soldaini, Alessandro Moschitti

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.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Answer SelectionQuestion AnsweringSentence

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Answer Selection ASNQ DeBERTa-V3-Large + SSP MAP 0.743 #1 of 3 Archive leaderboard report
Answer Selection ASNQ DeBERTa-V3-Large + SSP MRR 0.800 #1 of 3 Archive leaderboard report
Answer Selection ASNQ ELECTRA-Base + SSP MAP 0.697 #2 of 3 Archive leaderboard report
Answer Selection ASNQ ELECTRA-Base + SSP MRR 0.757 #2 of 3 Archive leaderboard report
Question Answering TrecQA DeBERTa-V3-Large + SSP MAP 0.923 #3 of 13 Archive leaderboard report
Question Answering TrecQA DeBERTa-V3-Large + SSP MRR 0.946 #3 of 13 Archive leaderboard report
Question Answering TrecQA RoBERTa-Base + PSD MAP 0.903 #7 of 13 Archive leaderboard report
Question Answering TrecQA RoBERTa-Base + PSD MRR 0.951 #7 of 13 Archive leaderboard report
Question Answering WikiQA DeBERTa-V3-Large + ALL MAP 0.909 #4 of 25 Archive leaderboard report
Question Answering WikiQA DeBERTa-V3-Large + ALL MRR 0.920 #4 of 25 Archive leaderboard report
Question Answering WikiQA DeBERTa-Large + SSP MAP 0.901 #5 of 25 Archive leaderboard report
Question Answering WikiQA DeBERTa-Large + SSP MRR 0.914 #5 of 25 Archive leaderboard report
Question Answering WikiQA RoBERTa-Base + SSP MAP 0.887 #7 of 25 Archive leaderboard report
Question Answering WikiQA RoBERTa-Base + SSP MRR 0.899 #7 of 25 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutELECTRALayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionRoBERTaSoftmaxWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections