自动化学报2016，Vol.42Issue(6)：807-818,12.DOI:10.16383/j.aas.2016.c150674
基于表示学习的知识库问答研究进展与展望
Representation Learning for Question Answering over Knowledge Base:An Overview
摘要
Abstract
Question answering over knowledge base (KBQA) is an important direction for the research of question answering. Recently, with the drastic development of deep learning, researchers and developers have paid more attentions to KBQA from this angle. They regarded this problem as a task of semantic matching. The semantics of knowledge base and users0 questions are learned through representation learning under the framework of deep learning. The entities and relations in knowledge base and the texts in questions could be represented as numerical vectors. Then, the answer could be figured out through similarity computation between the vectors of knowledge base and the vectors of the given question. From reported results, KBQA based on representation learning has obtained the best performance. This paper introduces the mainstream methods in this area. It further induces the typical approaches of representation learning on knowledge base and texts (questions), respectively. Finally, the current research challenges are discussed.关键词
知识库问答/深度学习/表示学习/语义分析Key words
Question answering over knowledge base (KBQA)/deep learning/representation learning/semantic analysis引用本文复制引用
刘康,张元哲,纪国良,来斯惟,赵军..基于表示学习的知识库问答研究进展与展望[J].自动化学报,2016,42(6):807-818,12.基金项目
国家重点基础研究发展计划(973计划)(2014CB340503),国家自然科学基金(61533018),“CCF-腾讯”犀牛鸟基金资助Supported by National Basic Research Program of China (973 Program)(2014CB340503), National Natural Science Founda-tion of China (61533018), and CCF-Tencent Open Research Fund （973计划）
