Abstract
In this research, we propose the task of question summarization. We first analyzed question-summary pairs extracted from a Community Question Answering (CQA) site, and found that a proportion of questions cannot be summarized by extractive approaches but requires abstractive approaches. We created a dataset by regarding the question-title pairs posted on the CQA site as question-summary pairs. By using the data, we trained extractive and abstractive summarization models, and compared them based on ROUGE scores and manual evaluations. Our experimental results show an abstractive method using an encoder-decoder model with a copying mechanism achieves better scores for both ROUGE-2 F-measure and the evaluations by human judges.- Anthology ID:
- I17-1080
- Volume:
- Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- November
- Year:
- 2017
- Address:
- Taipei, Taiwan
- Editors:
- Greg Kondrak, Taro Watanabe
- Venue:
- IJCNLP
- SIG:
- Publisher:
- Asian Federation of Natural Language Processing
- Note:
- Pages:
- 792–800
- Language:
- URL:
- https://aclanthology.org/I17-1080
- DOI:
- Cite (ACL):
- Tatsuya Ishigaki, Hiroya Takamura, and Manabu Okumura. 2017. Summarizing Lengthy Questions. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 792–800, Taipei, Taiwan. Asian Federation of Natural Language Processing.
- Cite (Informal):
- Summarizing Lengthy Questions (Ishigaki et al., IJCNLP 2017)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/I17-1080.pdf