Data Synthesis and Iterative Refinement for Neural Semantic Parsing without Annotated Logical Forms

Wu Shan, Chen Bo, Han Xianpei, Sun Le


Abstract
“Semantic parsing aims to convert natural language utterances to logical forms. A critical challenge for constructing semantic parsers is the lack of labeled data. In this paper, we propose a data synthesis and iterative refinement framework for neural semantic parsing, which can build semantic parsers without annotated logical forms. We first generate a naive corpus by sampling logic forms from knowledge bases and synthesizing their canonical utterances. Then, we further propose a bootstrapping algorithm to iteratively refine data and model, via a denoising language model and knowledge-constrained decoding. Experimental results show that our approach achieves competitive performance on GEO, ATIS and OVERNIGHT datasets in both unsupervised and semi-supervised data settings.”
Anthology ID:
2022.ccl-1.68
Volume:
Proceedings of the 21st Chinese National Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Nanchang, China
Editors:
Maosong Sun (孙茂松), Yang Liu (刘洋), Wanxiang Che (车万翔), Yang Feng (冯洋), Xipeng Qiu (邱锡鹏), Gaoqi Rao (饶高琦), Yubo Chen (陈玉博)
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
761–773
Language:
English
URL:
https://aclanthology.org/2022.ccl-1.68
DOI:
Bibkey:
Cite (ACL):
Wu Shan, Chen Bo, Han Xianpei, and Sun Le. 2022. Data Synthesis and Iterative Refinement for Neural Semantic Parsing without Annotated Logical Forms. In Proceedings of the 21st Chinese National Conference on Computational Linguistics, pages 761–773, Nanchang, China. Chinese Information Processing Society of China.
Cite (Informal):
Data Synthesis and Iterative Refinement for Neural Semantic Parsing without Annotated Logical Forms (Shan et al., CCL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.ccl-1.68.pdf