Knowledge Base Question Answering With a Matching-Aggregation Model and Question-Specific Contextual Relations

@article{Lan2019KnowledgeBQ,
  title={Knowledge Base Question Answering With a Matching-Aggregation Model and Question-Specific Contextual Relations},
  author={Yunshi Lan and Shuohang Wang and Jing Jiang},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
  year={2019},
  volume={27},
  pages={1629-1638}
}
Making use of knowledge bases to answer questions (KBQA) is a key direction in question answering systems. Researchers have developed a diverse range of methods to address this problem, but there are still some limitations with the existing methods. Specifically, the existing neural network-based methods for KBQA have not taken advantage of the recent “matching-aggregation” framework for the sequence matching, and when representing a candidate answer entity, they may not choose the most useful… CONTINUE READING