Semantic Parsing with Dual Learning

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 51–64 Florence, Italy, July 28 - August 2, 2019. c⃝2019 Association for Computational Linguistics 51 Semantic Parsing with Dual Learning Ruisheng Cao∗, Su Zhu∗, Chen Liu, Jieyu Li and Kai Yu † MoE Key Lab of Artificial Intelligence SpeechLab, Department of Computer Science and Engineering Shanghai Jiao Tong University, Shanghai, China {211314,paul2204,chris-chen,oracion,kai.yu}@sjtu.edu.cn Abstract Semantic parsing converts natural language queries into structured logical forms. The paucity of annotated training samples is a fundamental challenge in this field. In this work, we develop a semantic parsing frame- work with the dual learning algorithm, which enables a semantic parser to make full use of data (labeled and even unlabeled) through a dual-learning game. This game between a primal model (semantic parsing) and a dual model (logical form to query) forces them to regularize each other, and can achieve feed- back signals from some prior-knowledge. By utilizing the prior-knowledge of logical form structures, we propose a novel reward signal at the surface and semantic levels which tends to generate complete and reasonable logical forms. Experimental results show that our approach achieves new state-of-the-art perfor- mance on ATIS dataset and gets competitive performance on OVERNIGHT dataset. 1 Introduction Semantic parsing is the task of mapping a natu- ral language query into a logical form (Zelle and Mooney, 1996; Wong and Mooney, 2007; Zettle- moyer and Collins, 2007; Lu et al., 2008; Zettle- moyer and Collins, 2005). A logical form is one type of meaning representation understood by computers, which usually can be executed by an executor to obtain the answers. The successful application of recurrent neu- ral networks (RNN) in a variety of NLP tasks (Bahdanau et al., 2014; Sutskever et al., 2014; Vinyals et al., 2015) has provided strong impe- tus to treat semantic parsing as a sequence-to- sequence (Seq2seq) problem (Jia and Liang, 2016; Dong and Lapata, 2016). This approach generates ∗Ruisheng Cao and Su Zhu are co-first authors and con- tribute equally to this work. †The corresponding author is Kai Yu. a logical form based on the input query in an end- to-end manner but still leaves two main issues: (1) lack of labeled data and (2) constrained decoding. Firstly, semantic parsing relies on sufficient la- beled data. However, data annotation of semantic parsing is a labor-intensive and time-consuming task. Especially, the logical form is unfriendly for human annotation. Secondly, unlike natural language sentences, a logical form is strictly structured. For example, the lambda expression of “show flight from ci0 to ci1” is ( lambda $0 e ( and ( from $0 ci0 ) ( to $0 ci1 ) ( flight $0 ) ) ). If we make no constraint on decod- ing, the generated logical form may be invalid or incomplete at surface and semantic levels. Surface The generated sequence should be struc- tured as a complete logical form. For ex- ample, left and right parentheses should be matched to force the generated sequence to be a valid …

Content truncated to 500 words