Deep Learning for Answer Sentence Selection

4 Dec 2014Lei YuKarl Moritz HermannPhil BlunsomStephen 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... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Question Answering QASent Bigram-CNN MAP 0.5693 # 6
MRR 0.6613 # 6
Question Answering QASent Bigram-CNN (lexical overlap + dist output) MAP 0.7113 # 3
MRR 0.7846 # 3
Question Answering TrecQA CNN MAP 0.711 # 7
MRR 0.785 # 6
Question Answering WikiQA Bigram-CNN (lexical overlap + dist output) MAP 0.6520 # 14
MRR 0.6652 # 15
Question Answering WikiQA Bigram-CNN MAP 0.6190 # 15
MRR 0.6281 # 16