Combining Deep Learning with Information Retrieval for Question Answering

被引：14

作者：

Yang, Fengyu ^{[1
]}

Gan, Liang ^{[1
]}

Li, Aiping ^{[1
]}

Huang, Dongchuan ^{[1
]}

Chou, Xiaohui ^{[1
]}

Liu, Hongmei ^{[1
]}

机构：

[1] Natl Univ Def Technol, Dept Comp, Changsha, Hunan, Peoples R China

来源：

NATURAL LANGUAGE UNDERSTANDING AND INTELLIGENT APPLICATIONS (NLPCC 2016) | 2016年 / 10102卷

基金：

中国国家自然科学基金;

关键词：

Question answering; Deep learning; Information retrieval; Knowledge base;

D O I：

10.1007/978-3-319-50496-4_86

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents a system which learns to answer single-relation questions on a broad range of topics from a knowledge base using a three-layered learning system. Our system first learning a Topic Phrase Detecting model based on a phrase-entities dictionary to detect which phrase is the topic phrase of the question. The second layer of the system learning several answer ranking models. The last layer re-ranking the scores from the output of the second layer and return the highest scored answer. Both convolutional neural networks (CNN) and information retrieval (IR) models are included in this models. Training our system using pairs of questions and structured representations of their answers, yields competitive results on the NLPCC 2016 KBQA share task.

引用

页码：917 / 925

页数：9