Modeling transitions of focal entities for conversational knowledge base question answering

• Main Authors: LAN, Yunshi, JIANG, Jing
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: Computational linguistics; Graphic methods; Knowledge based systems; Natural language processing systems; Probability distributions; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/6779; https://ink.library.smu.edu.sg/context/sis_research/article/7782/viewcontent/2021.acl_long.255.pdf
• Institution: Singapore Management University

Conversational KBQA is about answering a sequence of questions related to a KB. Follow-up questions in conversational KBQA often have missing information referring to entities from the conversation history. In this paper, we propose to model these implied entities, which we refer to as the focal entities of the conversation. We propose a novel graph-based model to capture the transitions of focal entities and apply a graph neural network to derive a probability distribution of focal entities for each question, which is then combined with a standard KBQA module to perform answer ranking. Our experiments on two datasets demonstrate the effectiveness of our proposed method.