@article{Qiu_Huang_Chen_Ji_Qu_Wei_Huang_Zhang_2021, title={Reinforced History Backtracking for Conversational Question Answering}, volume={35}, url={https://ojs.aaai.org/index.php/AAAI/article/view/17617}, DOI={10.1609/aaai.v35i15.17617}, abstractNote={To model the context history in multi-turn conversations has become a critical step towards a better understanding of the user query in question answering systems. To utilize the context history, most existing studies treat the whole context as input, which will inevitably face the following two challenges. First, modeling a long history can be costly as it requires more computation resources. Second, the long context history consists of a lot of irrelevant information that makes it difficult to model appropriate information relevant to the user query. To alleviate these problems, we propose a reinforcement learning based method to capture and backtrack the related conversation history to boost model performance in this paper. Our method seeks to automatically backtrack the history information with the implicit feedback from the model performance. We further consider both immediate and delayed rewards to guide the reinforced backtracking policy. Extensive experiments on a large conversational question answering dataset show that the proposed method can help to alleviate the problems arising from longer context history. Meanwhile, experiments show that the method yields better performance than other strong baselines, and the actions made by the method are insightful.}, number={15}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Qiu, Minghui and Huang, Xinjing and Chen, Cen and Ji, Feng and Qu, Chen and Wei, Wei and Huang, Jun and Zhang, Yin}, year={2021}, month={May}, pages={13718-13726} }