Knowledge Graph Embedding Based Question Answering

被引:384
作者
Huang, Xiao [1 ]
Zhang, Jingyuan [1 ]
Li, Dingcheng [1 ]
Li, Ping [1 ]
机构
[1] Baidu Res, Cognit Comp Lab, Sunnyvale, CA 94089 USA
来源
PROCEEDINGS OF THE TWELFTH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING (WSDM'19) | 2019年
关键词
Question answering; knowledge graph embedding; deep learning;
D O I
10.1145/3289600.3290956
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Question answering over knowledge graph (QA-KG) aims to use facts in the knowledge graph (KG) to answer natural language questions. It helps end users more efficiently and more easily access the substantial and valuable knowledge in the KG, without knowing its data structures. QA-KG is a nontrivial problem since capturing the semantic meaning of natural language is difficult for a machine. Meanwhile, many knowledge graph embedding methods have been proposed. The key idea is to represent each predicate/entity as a low-dimensional vector, such that the relation information in the KG could be preserved. The learned vectors could benefit various applications such as KG completion and recommender systems. In this paper, we explore to use them to handle the QA-KG problem. However, this remains a challenging task since a predicate could be expressed in different ways in natural language questions. Also, the ambiguity of entity names and partial names makes the number of possible answers large. To bridge the gap, we propose an effective Knowledge Embedding based Question Answering (KEQA) framework. We focus on answering the most common types of questions, i.e., simple questions, in which each question could be answered by the machine straightforwardly if its single head entity and single predicate are correctly identified. To answer a simple question, instead of inferring its head entity and predicate directly, KEQA targets at jointly recovering the question's head entity, predicate, and tail entity representations in the KG embedding spaces. Based on a carefully-designed joint distance metric, the three learned vectors' closest fact in the KG is returned as the answer. Experiments on a widely-adopted benchmark demonstrate that the proposed KEQA outperforms the state-of-the-art QA-KG methods.
引用
收藏
页码:105 / 113
页数:9
相关论文
共 50 条
[1]  
[Anonymous], 2015, P 3 WORKSH CONT VECT
[2]  
Bahdanau D, 2016, Arxiv, DOI arXiv:1409.0473
[3]  
Bao J., 2016, P COLING 2016 26 INT, P2503
[4]  
Berant Jonathan, 2013, P 2013 C EMPIRICAL M, P1533
[5]   Fast and Space-Efficient Entity Linking in Queries [J].
Blanco, Roi ;
Ottaviano, Giuseppe ;
Meij, Edgar .
WSDM'15: PROCEEDINGS OF THE EIGHTH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING, 2015, :179-188
[6]  
Bordes A., 2011, P AAAI C ART INT, P301, DOI DOI 10.1609/AAAI.V25I1.7917
[7]  
Bordes A., 2014, JOINT EUR C MACH LEA, V8724, P165
[8]  
Bordes A., 2015, ABS150602075 CORR
[9]  
Bordes A, 2013, ADV NEURAL INFORM PR, V26
[10]  
Bordes Antoine, 2014, Question answering with subgraph embeddings