Abstract
The neural seq2seq based question generation (QG) is prone to generating generic and undiversified questions that are poorly relevant to the given passage and target answer. In this paper, we propose two methods to address the issue. (1) By a partial copy mechanism, we prioritize words that are morphologically close to words in the input passage when generating questions; (2) By a QA-based reranker, from the n-best list of question candidates, we select questions that are preferred by both the QA and QG model. Experiments and analyses demonstrate that the proposed two methods substantially improve the relevance of generated questions to passages and answers.- Anthology ID:
- D19-1614
- Volume:
- Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Editors:
- Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
- Venues:
- EMNLP | IJCNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5983–5987
- Language:
- URL:
- https://aclanthology.org/D19-1614
- DOI:
- 10.18653/v1/D19-1614
- Cite (ACL):
- Jiazuo Qiu and Deyi Xiong. 2019. Generating Highly Relevant Questions. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5983–5987, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- Generating Highly Relevant Questions (Qiu & Xiong, EMNLP-IJCNLP 2019)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/D19-1614.pdf
- Data
- SQuAD