A reinforcement learning formulation to the complex question answering problem

作者：

Highlights：

• Reinforcement learning formulation for complex question answering.

• Abstract summaries used for small amount of supervision using reward scores.

• User interaction component incorporated to guide candidate sentence selection.

• Experiments reveal that systems trained with user interaction perform better.

• The reinforcement system is able to learn automatically and effectively.

摘要

•Reinforcement learning formulation for complex question answering.•Abstract summaries used for small amount of supervision using reward scores.•User interaction component incorporated to guide candidate sentence selection.•Experiments reveal that systems trained with user interaction perform better.•The reinforcement system is able to learn automatically and effectively.

论文关键词：Complex question answering,Multi-document summarization,Reinforcement learning,Reward function,User interaction modeling

论文评审过程：Received 23 July 2012, Revised 26 December 2014, Accepted 5 January 2015, Available online 24 February 2015.

论文官网地址：https://doi.org/10.1016/j.ipm.2015.01.002