An enhanced convolutional neural network model for answer selection

Jiahui GUO, Bin YUE, Guandong XU, Zhenglu YANG, Jin Mao WEI

Research output: Chapter in Book/Report/Conference proceedingChapters

19 Citations (Scopus)

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. Copyright © 2017 International World Wide Web Conference Committee (IW3C2), published under Creative Commons CC BY 4.0 License.

Original languageEnglish
Title of host publicationProceedings of the 26th International Conference on World Wide Web, WWW 2017
Place of PublicationUSA
PublisherThe Association for Computing Machinery
Pages789-790
ISBN (Electronic)9781450349147
DOIs
Publication statusPublished - 2017

Citation

Guo, J., Yue, B., Xu, G., Yang, Z., & Wei, J.-M. (2017). An enhanced convolutional neural network model for answer selection. In Proceedings of the 26th International Conference on World Wide Web, WWW 2017 (pp. 789-790). The Association for Computing Machinery. https://doi.org/10.1145/3041021.3054216

Fingerprint

Dive into the research topics of 'An enhanced convolutional neural network model for answer selection'. Together they form a unique fingerprint.