Paper Info
Title
Open Domain Question Answering with Character-Level Deep Learning Models
Abstract
Single-relation factoid question answering (QA) is strongly supported by rich sources of facts from knowledge bases (KB). However, there are many irrelevant information in questions and overwhelming number of facts in knowledge bases, mak-ing it difficult to capture goal entity and relation involved in a question. In order to settle these issues, firstly, a state-of-the-art sequence tagging model (BiLSTM-CRF) is adopted to detect the entity mention in a question. Then, we propose a n-gram match (NGM) algorithm with Chinese-specific rules and an attention-based siamese bidirectional long-short term memory (ASBLSTM) model to measure the lexical and se-mantic similarity between questions and candidate facts. Our whole method requires no hand-crafted template or feature engineering. In addition, character-level models are proved to be effective in solving the out of vocabulary (OOV) issue and improving the accuracy in Chinese KBQA task. Experiment results show that our system outperforms the best system with deep learning models in the KBQA share task of the Confer-ence on Natural Language Processing and Chinese Compu-ting (NLPCC) 2016 and our system achieves an AverageF1 measure of 80.97% and 37.18% on test dataset in NLPCC 2016 and 2017 respectively.
Year
DOI
Venue
2017
10.1109/ISCID.2017.58
2017 10th International Symposium on Computational Intelligence and Design (ISCID)
Keywords
Field
DocType
Knowledge Base Question Answering,Entity Extraction,Relation Recognition,Entity Linking
Question answering,Task analysis,Computer science,Knowledge-based systems,Feature engineering,Natural language processing,Artificial intelligence,Knowledge extraction,Deep learning,Factoid,Machine learning,Semantics
Conference
Volume
ISSN
ISBN
2
2165-1701
978-1-5386-3676-3
Citations 
PageRank 
References 
2
0.41
5
Authors
4
Name
Order
Citations
PageRank
Lei Kai115738.17
Yang Deng2113.78
Bing Zhang3167.97
Shen Ying47323.48