Documents
Poster
History Question Classification and Representation for Chinese Gaokao
- Citation Author(s):
- Submitted by:
- Ke Yu
- Last updated:
- 21 November 2016 - 9:27pm
- Document Type:
- Poster
- Document Year:
- 2016
- Event:
- Presenters:
- Ke Yu
- Paper Code:
- 80
- Categories:
- Log in to post comments
In this paper, we propose a question representation based on entity labeling and question classification for a automatic question answering system of Chinese Gaokao history question. A CRF model is used for the entity labeling and SVM/CNN/LSTM models are tested for question classification. Our experiments show that CRF model provides a high performance when used to label informative entities out while neural networks has a promising performance for the question classification task. With both entity labeling and question classification models of high performance, we can provide the KB-based question answering system with a question representation of high reliability. Then the question answering system can do more good work depending on the key information our models provide.