A Multi-Task Learning Approach for Answer Selection: A Study and a Chinese Law Dataset


  • Wenyu Du Westlake University
  • Baocheng Li Chinese Academy of Sciences
  • Min Yang Chinese Academy of Sciences
  • Qiang Qu Chinese Academy of Sciences
  • Ying Shen Peking University




In this paper, we propose a Multi-Task learning approach for Answer Selection (MTAS), motivated by the fact that humans have no difficulty performing such task because they possess capabilities of multiple domains (tasks). Specifically, MTAS consists of two key components: (i) A category classification model that learns rich category-aware document representation; (ii) An answer selection model that provides the matching scores of question-answer pairs. These two tasks work on a shared document encoding layer, and they cooperate to learn a high-quality answer selection system. In addition, a multi-head attention mechanism is proposed to learn important information from different representation subspaces at different positions. We manually annotate the first Chinese question answering dataset in law domain (denoted as LawQA) to evaluate the effectiveness of our model. The experimental results show that our model MTAS consistently outperforms the compared methods.1




How to Cite

Du, W., Li, B., Yang, M., Qu, Q., & Shen, Y. (2019). A Multi-Task Learning Approach for Answer Selection: A Study and a Chinese Law Dataset. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 9935-9936. https://doi.org/10.1609/aaai.v33i01.33019935



Student Abstract Track