Abstract
Question classification is an important task with wide applications. However, traditional techniques treat questions as general sentences, ignoring the corresponding answer data. In order to consider answer information into question modeling, we first introduce novel group sparse autoencoders which refine question representation by utilizing group information in the answer set. We then propose novel group sparse CNNs which naturally learn question representation with respect to their answers by implanting group sparse autoencoders into traditional CNNs. The proposed model significantly outperform strong baselines on four datasets.- Anthology ID:
- P17-2053
- Volume:
- Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Month:
- July
- Year:
- 2017
- Address:
- Vancouver, Canada
- Editors:
- Regina Barzilay, Min-Yen Kan
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 335–340
- Language:
- URL:
- https://aclanthology.org/P17-2053
- DOI:
- 10.18653/v1/P17-2053
- Cite (ACL):
- Mingbo Ma, Liang Huang, Bing Xiang, and Bowen Zhou. 2017. Group Sparse CNNs for Question Classification with Answer Sets. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 335–340, Vancouver, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Group Sparse CNNs for Question Classification with Answer Sets (Ma et al., ACL 2017)
- PDF:
- https://preview.aclanthology.org/ml4al-ingestion/P17-2053.pdf