An Enhanced Convolutional Neural Network Model for Answer Selection
- Publication Type:
- Conference Proceeding
- Proceeding WWW '17 Companion Proceedings of the 26th International Conference on World Wide Web Companion, 2017, pp. 789 - 790
- Issue Date:
Files in This Item:
|An Enhanced Convolutional Neural Network Model for Answer Selection.pdf||Accepted Manuscript version||639.36 kB|
Copyright Clearance Process
- Recently Added
- In Progress
- Open Access
This item is open access.
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 op- timization strategies. The intuitive idea is that the granular representations with more semantic features of sentences are deliberately designed and estimated to capture the similar- ity between question-answer pairwise sentences. The experi- mental 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.
Please use this identifier to cite or link to this item: