@inproceedings{zheng-etal-2023-grammar,
title = "Grammar-based Decoding for Improved Compositional Generalization in Semantic Parsing",
author = "Zheng, Jing and
Chow, Jyh-Herng and
Shen, Zhongnan and
Xu, Peng",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.91",
doi = "10.18653/v1/2023.findings-acl.91",
pages = "1399--1418",
abstract = "Sequence-to-sequence (seq2seq) models have achieved great success in semantic parsing tasks, but they tend to struggle on out-of-distribution (OOD) data. Despite recent progress, robust semantic parsing on large-scale tasks with combined challenges from both compositional generalization and natural language variations remains an unsolved problem. To promote research in this area, this work presents CUDON, a large-scale dialogue dataset in Chinese language, particularly designed for evaluating compositional generalization of semantic parsing. The dataset contains about ten thousand multi-turn complex queries, and provides multiple splits with different degrees of train-test distribution divergence. We have investigated improving compositional generalization with grammar-based decodering on this dataset. With specially designed grammars leveraging program schema, we are able to substantially improve accuracy of seq2seq semantic parsers on OOD splits: A LSTM-based parser using a Context-free Grammar (CFG) achieves over 25{\%} higher accuracy than a standard seq2seq baseline; a parser using Tree-Substitution Grammar (TSG) improves parsing speed five to seven times over the CFG parser with only a small accuracy loss. The grammar-based LSTM parsers also outperforms BART- and T5-based seq2seq parsers on the OOD splits, despite having less than one tenth of parameters and no pretraining. We also verified our approach on the SMCalflow-CS dataset, particularly, on the zero-shot learning task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-etal-2023-grammar">
<titleInfo>
<title>Grammar-based Decoding for Improved Compositional Generalization in Semantic Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jyh-Herng</namePart>
<namePart type="family">Chow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongnan</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sequence-to-sequence (seq2seq) models have achieved great success in semantic parsing tasks, but they tend to struggle on out-of-distribution (OOD) data. Despite recent progress, robust semantic parsing on large-scale tasks with combined challenges from both compositional generalization and natural language variations remains an unsolved problem. To promote research in this area, this work presents CUDON, a large-scale dialogue dataset in Chinese language, particularly designed for evaluating compositional generalization of semantic parsing. The dataset contains about ten thousand multi-turn complex queries, and provides multiple splits with different degrees of train-test distribution divergence. We have investigated improving compositional generalization with grammar-based decodering on this dataset. With specially designed grammars leveraging program schema, we are able to substantially improve accuracy of seq2seq semantic parsers on OOD splits: A LSTM-based parser using a Context-free Grammar (CFG) achieves over 25% higher accuracy than a standard seq2seq baseline; a parser using Tree-Substitution Grammar (TSG) improves parsing speed five to seven times over the CFG parser with only a small accuracy loss. The grammar-based LSTM parsers also outperforms BART- and T5-based seq2seq parsers on the OOD splits, despite having less than one tenth of parameters and no pretraining. We also verified our approach on the SMCalflow-CS dataset, particularly, on the zero-shot learning task.</abstract>
<identifier type="citekey">zheng-etal-2023-grammar</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.91</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.91</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1399</start>
<end>1418</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Grammar-based Decoding for Improved Compositional Generalization in Semantic Parsing
%A Zheng, Jing
%A Chow, Jyh-Herng
%A Shen, Zhongnan
%A Xu, Peng
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F zheng-etal-2023-grammar
%X Sequence-to-sequence (seq2seq) models have achieved great success in semantic parsing tasks, but they tend to struggle on out-of-distribution (OOD) data. Despite recent progress, robust semantic parsing on large-scale tasks with combined challenges from both compositional generalization and natural language variations remains an unsolved problem. To promote research in this area, this work presents CUDON, a large-scale dialogue dataset in Chinese language, particularly designed for evaluating compositional generalization of semantic parsing. The dataset contains about ten thousand multi-turn complex queries, and provides multiple splits with different degrees of train-test distribution divergence. We have investigated improving compositional generalization with grammar-based decodering on this dataset. With specially designed grammars leveraging program schema, we are able to substantially improve accuracy of seq2seq semantic parsers on OOD splits: A LSTM-based parser using a Context-free Grammar (CFG) achieves over 25% higher accuracy than a standard seq2seq baseline; a parser using Tree-Substitution Grammar (TSG) improves parsing speed five to seven times over the CFG parser with only a small accuracy loss. The grammar-based LSTM parsers also outperforms BART- and T5-based seq2seq parsers on the OOD splits, despite having less than one tenth of parameters and no pretraining. We also verified our approach on the SMCalflow-CS dataset, particularly, on the zero-shot learning task.
%R 10.18653/v1/2023.findings-acl.91
%U https://aclanthology.org/2023.findings-acl.91
%U https://doi.org/10.18653/v1/2023.findings-acl.91
%P 1399-1418
Markdown (Informal)
[Grammar-based Decoding for Improved Compositional Generalization in Semantic Parsing](https://aclanthology.org/2023.findings-acl.91) (Zheng et al., Findings 2023)
ACL