@inproceedings{lent-etal-2021-testing,
title = "Testing Cross-Database Semantic Parsers With Canonical Utterances",
author = "Lent, Heather and
Yavuz, Semih and
Yu, Tao and
Niu, Tong and
Zhou, Yingbo and
Radev, Dragomir and
Lin, Xi Victoria",
editor = "Gao, Yang and
Eger, Steffen and
Zhao, Wei and
Lertvittayakumjorn, Piyawat and
Fomicheva, Marina",
booktitle = "Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eval4nlp-1.8",
doi = "10.18653/v1/2021.eval4nlp-1.8",
pages = "73--83",
abstract = "The benchmark performance of cross-database semantic parsing has climbed steadily in recent years, catalyzed by the wide adoption of pre-trained language models. Yet existing work have shown that state-of-the-art cross-database semantic parsers struggle to generalize to novel user utterances, databases and query structures. To obtain transparent details on the strengths and limitation of these models, we propose a diagnostic testing approach based on controlled synthesis of canonical natural language and SQL pairs. Inspired by the CheckList, we characterize a set of essential capabilities for cross-database semantic parsing models, and detailed the method for synthesizing the corresponding test data. We evaluated a variety of high performing models using the proposed approach, and identified several non-obvious weaknesses across models (e.g. unable to correctly select many columns). Our dataset and code are released as a test suite at \url{http://github.com/hclent/BehaviorCheckingSemPar}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lent-etal-2021-testing">
<titleInfo>
<title>Testing Cross-Database Semantic Parsers With Canonical Utterances</title>
</titleInfo>
<name type="personal">
<namePart type="given">Heather</namePart>
<namePart type="family">Lent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Semih</namePart>
<namePart type="family">Yavuz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Niu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingbo</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dragomir</namePart>
<namePart type="family">Radev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="given">Victoria</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steffen</namePart>
<namePart type="family">Eger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piyawat</namePart>
<namePart type="family">Lertvittayakumjorn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marina</namePart>
<namePart type="family">Fomicheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The benchmark performance of cross-database semantic parsing has climbed steadily in recent years, catalyzed by the wide adoption of pre-trained language models. Yet existing work have shown that state-of-the-art cross-database semantic parsers struggle to generalize to novel user utterances, databases and query structures. To obtain transparent details on the strengths and limitation of these models, we propose a diagnostic testing approach based on controlled synthesis of canonical natural language and SQL pairs. Inspired by the CheckList, we characterize a set of essential capabilities for cross-database semantic parsing models, and detailed the method for synthesizing the corresponding test data. We evaluated a variety of high performing models using the proposed approach, and identified several non-obvious weaknesses across models (e.g. unable to correctly select many columns). Our dataset and code are released as a test suite at http://github.com/hclent/BehaviorCheckingSemPar.</abstract>
<identifier type="citekey">lent-etal-2021-testing</identifier>
<identifier type="doi">10.18653/v1/2021.eval4nlp-1.8</identifier>
<location>
<url>https://aclanthology.org/2021.eval4nlp-1.8</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>73</start>
<end>83</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Testing Cross-Database Semantic Parsers With Canonical Utterances
%A Lent, Heather
%A Yavuz, Semih
%A Yu, Tao
%A Niu, Tong
%A Zhou, Yingbo
%A Radev, Dragomir
%A Lin, Xi Victoria
%Y Gao, Yang
%Y Eger, Steffen
%Y Zhao, Wei
%Y Lertvittayakumjorn, Piyawat
%Y Fomicheva, Marina
%S Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F lent-etal-2021-testing
%X The benchmark performance of cross-database semantic parsing has climbed steadily in recent years, catalyzed by the wide adoption of pre-trained language models. Yet existing work have shown that state-of-the-art cross-database semantic parsers struggle to generalize to novel user utterances, databases and query structures. To obtain transparent details on the strengths and limitation of these models, we propose a diagnostic testing approach based on controlled synthesis of canonical natural language and SQL pairs. Inspired by the CheckList, we characterize a set of essential capabilities for cross-database semantic parsing models, and detailed the method for synthesizing the corresponding test data. We evaluated a variety of high performing models using the proposed approach, and identified several non-obvious weaknesses across models (e.g. unable to correctly select many columns). Our dataset and code are released as a test suite at http://github.com/hclent/BehaviorCheckingSemPar.
%R 10.18653/v1/2021.eval4nlp-1.8
%U https://aclanthology.org/2021.eval4nlp-1.8
%U https://doi.org/10.18653/v1/2021.eval4nlp-1.8
%P 73-83
Markdown (Informal)
[Testing Cross-Database Semantic Parsers With Canonical Utterances](https://aclanthology.org/2021.eval4nlp-1.8) (Lent et al., Eval4NLP 2021)
ACL
- Heather Lent, Semih Yavuz, Tao Yu, Tong Niu, Yingbo Zhou, Dragomir Radev, and Xi Victoria Lin. 2021. Testing Cross-Database Semantic Parsers With Canonical Utterances. In Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems, pages 73–83, Punta Cana, Dominican Republic. Association for Computational Linguistics.