Deep Learning for Answer Sentence Selection

4 Dec 2014  ·  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.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
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 # 13
MRR 0.785 # 12
Question Answering WikiQA Bigram-CNN MAP 0.6190 # 23
MRR 0.6281 # 23
Question Answering WikiQA Bigram-CNN (lexical overlap + dist output) MAP 0.6520 # 21
MRR 0.6652 # 21

Methods


No methods listed for this paper. Add relevant methods here