Paper Info
Title
An Enhanced Convolutional Neural Network Model for Answer Selection.
Abstract
Answer selection is an important task in question answering (QA) from the Web. To address the intrinsic difficulty in encoding sentences with semantic meanings, we introduce a general framework, i.e., Lexical Semantic Feature based Skip Convolution Neural Network (LSF-SCNN), with several optimization strategies. The intuitive idea is that the granular representations with more semantic features of sentences are deliberately designed and estimated to capture the similarity between question-answer pairwise sentences. The experimental results demonstrate the effectiveness of the proposed strategies and our model outperforms the state-of-the-art ones by up to 3.5% on the metrics of MAP and MRR.
Year
DOI
Venue
2017
10.1145/3041021.3054216
WWW (Companion Volume)
Field
DocType
Citations 
Pairwise comparison,Data mining,World Wide Web,Question answering,Computer science,Convolutional neural network,Natural language processing,Artificial intelligence,Semantic feature,Encoding (memory)
Conference
2
PageRank 
References 
Authors
0.43
6
5
Name
Order
Citations
PageRank
Jiahui Guo121.79
Bin Yue222.80
Guandong Xu364075.03
Zhenglu Yang425735.45
Jun Wang522.80