Reinforced Question Rewriting for Conversational Question Answering
Chen, Zhiyu, Zhao, Jie, Fang, Anjie, Fetahu, Besnik, Rokhlenko, Oleg, Malmasi, Shervin
–arXiv.org Artificial Intelligence
Conversational Question Answering (CQA) aims to answer questions contained within dialogues, which are not easily interpretable without context. Developing a model to rewrite conversational questions into self-contained ones is an emerging solution in industry settings as it allows using existing single-turn QA systems to avoid training a CQA model from scratch. Previous work trains rewriting models using human rewrites as supervision. However, such objectives are disconnected with QA models and therefore more human-like rewrites do not guarantee better QA performance. In this paper we propose using QA feedback to supervise the rewriting model with reinforcement learning. Experiments show that our approach can effectively improve QA performance over baselines for both extractive and retrieval QA. Furthermore, human evaluation shows that our method can generate more accurate and detailed rewrites when compared to human annotations.
arXiv.org Artificial Intelligence
Oct-31-2022
- Country:
- Oceania > Australia
- North America
- United States
- Washington > King County
- Seattle (0.04)
- Texas > Travis County
- Austin (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Washington > King County
- Puerto Rico > San Juan
- San Juan (0.04)
- United States
- Europe > Spain
- Catalonia > Barcelona Province > Barcelona (0.04)
- Asia
- Middle East > Jordan (0.04)
- China > Hong Kong (0.04)
- Africa > Nigeria
- Genre:
- Research Report > Experimental Study (0.93)
- Industry:
- Media (0.47)
- Leisure & Entertainment (0.47)
- Technology: