Convolutional Interaction Network for Natural Language Inference
Jingjing Gong, Xipeng Qiu, Xinchi Chen, Dong Liang, Xuanjing Huang
Abstract
Attention-based neural models have achieved great success in natural language inference (NLI). In this paper, we propose the Convolutional Interaction Network (CIN), a general model to capture the interaction between two sentences, which can be an alternative to the attention mechanism for NLI. Specifically, CIN encodes one sentence with the filters dynamically generated based on another sentence. Since the filters may be designed to have various numbers and sizes, CIN can capture more complicated interaction patterns. Experiments on three large datasets demonstrate CIN’s efficacy.- Anthology ID:
- D18-1186
- Volume:
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Month:
- October-November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1576–1585
- Language:
- URL:
- https://aclanthology.org/D18-1186
- DOI:
- 10.18653/v1/D18-1186
- Cite (ACL):
- Jingjing Gong, Xipeng Qiu, Xinchi Chen, Dong Liang, and Xuanjing Huang. 2018. Convolutional Interaction Network for Natural Language Inference. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1576–1585, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Convolutional Interaction Network for Natural Language Inference (Gong et al., EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/D18-1186.pdf
- Data
- MultiNLI, SNLI