Papers › Deep Learning for Answer Sentence Selection

Deep Learning for Answer Sentence Selection

4 Dec 2014arXiv:1412.1632archive 2025-07-28

Lei Yu, Karl Moritz Hermann, Phil Blunsom, Stephen Pulman

Answer sentence selection is the task of identifying sentences that contain the answer to a given question. This is an important problem in its own right as well as in the larger context of open domain question answering. We propose a novel approach to solving this task via means of distributed representations, and learn to match questions with answers by considering their semantic encoding. This contrasts prior work on this task, which typically relies on classifiers with large numbers of hand-crafted syntactic and semantic features and various external resources. Our approach does not require any feature engineering nor does it involve specialist linguistic data, making this model easily applicable to a wide range of domains and languages. Experimental results on a standard benchmark dataset from TREC demonstrate that---despite its simplicity---our model matches state of the art performance on the answer sentence selection task.

PaperPDFCode

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

Code

brmson/dataset-sts mentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

Deep LearningFeature EngineeringOpen-Domain Question AnsweringQuestion AnsweringSentence

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering QASent Bigram-CNN (lexical overlap + dist output) MAP 0.7113 #3 of 7 Archive leaderboard report
Question Answering QASent Bigram-CNN (lexical overlap + dist output) MRR 0.7846 #3 of 7 Archive leaderboard report
Question Answering QASent Bigram-CNN MAP 0.5693 #6 of 7 Archive leaderboard report
Question Answering QASent Bigram-CNN MRR 0.6613 #6 of 7 Archive leaderboard report
Question Answering TrecQA CNN MAP 0.711 #13 of 13 Archive leaderboard report
Question Answering TrecQA CNN MRR 0.785 #13 of 13 Archive leaderboard report
Question Answering WikiQA Bigram-CNN (lexical overlap + dist output) MAP 0.6520 #21 of 25 Archive leaderboard report
Question Answering WikiQA Bigram-CNN (lexical overlap + dist output) MRR 0.6652 #21 of 25 Archive leaderboard report
Question Answering WikiQA Bigram-CNN MAP 0.6190 #23 of 25 Archive leaderboard report
Question Answering WikiQA Bigram-CNN MRR 0.6281 #23 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.

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