ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs

Wenpeng Yin, Hinrich Schütze, Bing Xiang, Bowen Zhou


Abstract
How to model a pair of sentences is a critical issue in many NLP tasks such as answer selection (AS), paraphrase identification (PI) and textual entailment (TE). Most prior work (i) deals with one individual task by fine-tuning a specific system; (ii) models each sentence’s representation separately, rarely considering the impact of the other sentence; or (iii) relies fully on manually designed, task-specific linguistic features. This work presents a general Attention Based Convolutional Neural Network (ABCNN) for modeling a pair of sentences. We make three contributions. (i) The ABCNN can be applied to a wide variety of tasks that require modeling of sentence pairs. (ii) We propose three attention schemes that integrate mutual influence between sentences into CNNs; thus, the representation of each sentence takes into consideration its counterpart. These interdependent sentence pair representations are more powerful than isolated sentence representations. (iii) ABCNNs achieve state-of-the-art performance on AS, PI and TE tasks. We release code at: https://github.com/yinwenpeng/Answer_Selection.
Anthology ID:
Q16-1019
Erratum e1:
Q16-1019e1
Volume:
Transactions of the Association for Computational Linguistics, Volume 4
Month:
Year:
2016
Address:
Cambridge, MA
Editors:
Lillian Lee, Mark Johnson, Kristina Toutanova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
259–272
Language:
URL:
https://aclanthology.org/Q16-1019
DOI:
10.1162/tacl_a_00097
Bibkey:
Cite (ACL):
Wenpeng Yin, Hinrich Schütze, Bing Xiang, and Bowen Zhou. 2016. ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs. Transactions of the Association for Computational Linguistics, 4:259–272.
Cite (Informal):
ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs (Yin et al., TACL 2016)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/Q16-1019.pdf
Code
 yinwenpeng/Answer_Selection +  additional community code
Data
SICKWikiQA