Semantic Parsing via Paraphrasing

被引:233
作者
Berant, Jonathan [1 ]
Liang, Percy [1 ]
机构
[1] Stanford Univ, Stanford, CA 94305 USA
来源
PROCEEDINGS OF THE 52ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1 | 2014年
关键词
D O I
10.3115/v1/p14-1133
中图分类号
TP18 [人工智能理论];
学科分类号
140502 [人工智能];
摘要
A central challenge in semantic parsing is handling the myriad ways in which knowledge base predicates can be expressed. Traditionally, semantic parsers are trained primarily from text paired with knowledge base information. Our goal is to exploit the much larger amounts of raw text not tied to any knowledge base. In this paper, we turn semantic parsing on its head. Given an input utterance, we first use a simple method to deterministically generate a set of candidate logical forms with a canonical realization in natural language for each. Then, we use a paraphrase model to choose the realization that best paraphrases the input, and output the corresponding logical form. We present two simple paraphrase models, an association model and a vector space model, and train them jointly from question-answer pairs. Our system PARASEMPRE improves state-of-the-art accuracies on two recently released question-answering datasets.
引用
收藏
页码:1415 / 1425
页数:11
相关论文
共 35 条
[1]
[Anonymous], 2007, P 45 ANN M ASS COMP
[2]
[Anonymous], EMPIRICAL METHODS NA
[3]
[Anonymous], ASS COMPUTATIONAL LI
[4]
[Anonymous], C LEARN THEOR COLT
[5]
[Anonymous], 1998, WordNet
[6]
[Anonymous], 2011, Advances in Neural Information Processing Systems
[7]
[Anonymous], LAMBDA DEPENDENCY BA
[8]
[Anonymous], 2005, ACL, DOI 10.3115/1219840.1219885
[9]
Berant J., 2013, SEMANTIC PARSING FRE
[10]
Chang M., 2010, N AM ASS COMPUTATION