@inproceedings{glenn-etal-2023-correcting,
title = "Correcting Semantic Parses with Natural Language through Dynamic Schema Encoding",
author = "Glenn, Parker and
Dakle, Parag Pravin and
Raghavan, Preethi",
editor = "Chen, Yun-Nung and
Rastogi, Abhinav",
booktitle = "Proceedings of the 5th Workshop on NLP for Conversational AI (NLP4ConvAI 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.nlp4convai-1.3",
doi = "10.18653/v1/2023.nlp4convai-1.3",
pages = "29--38",
abstract = "In addressing the task of converting natural language to SQL queries, there are several semantic and syntactic challenges. It becomes increasingly important to understand and remedy the points of failure as the performance of semantic parsing systems improve. We explore semantic parse correction with natural language feedback, proposing a new solution built on the success of autoregressive decoders in text-to-SQL tasks. By separating the semantic and syntactic difficulties of the task, we show that the accuracy of text-to-SQL parsers can be boosted by up to 26{\%} with only one turn of correction with natural language. Additionally, we show that a T5-base model is capable of correcting the errors of a T5-large model in a zero-shot, cross-parser setting.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="glenn-etal-2023-correcting">
<titleInfo>
<title>Correcting Semantic Parses with Natural Language through Dynamic Schema Encoding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Parker</namePart>
<namePart type="family">Glenn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parag</namePart>
<namePart type="given">Pravin</namePart>
<namePart type="family">Dakle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preethi</namePart>
<namePart type="family">Raghavan</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>Proceedings of the 5th Workshop on NLP for Conversational AI (NLP4ConvAI 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Rastogi</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>In addressing the task of converting natural language to SQL queries, there are several semantic and syntactic challenges. It becomes increasingly important to understand and remedy the points of failure as the performance of semantic parsing systems improve. We explore semantic parse correction with natural language feedback, proposing a new solution built on the success of autoregressive decoders in text-to-SQL tasks. By separating the semantic and syntactic difficulties of the task, we show that the accuracy of text-to-SQL parsers can be boosted by up to 26% with only one turn of correction with natural language. Additionally, we show that a T5-base model is capable of correcting the errors of a T5-large model in a zero-shot, cross-parser setting.</abstract>
<identifier type="citekey">glenn-etal-2023-correcting</identifier>
<identifier type="doi">10.18653/v1/2023.nlp4convai-1.3</identifier>
<location>
<url>https://aclanthology.org/2023.nlp4convai-1.3</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>29</start>
<end>38</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Correcting Semantic Parses with Natural Language through Dynamic Schema Encoding
%A Glenn, Parker
%A Dakle, Parag Pravin
%A Raghavan, Preethi
%Y Chen, Yun-Nung
%Y Rastogi, Abhinav
%S Proceedings of the 5th Workshop on NLP for Conversational AI (NLP4ConvAI 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F glenn-etal-2023-correcting
%X In addressing the task of converting natural language to SQL queries, there are several semantic and syntactic challenges. It becomes increasingly important to understand and remedy the points of failure as the performance of semantic parsing systems improve. We explore semantic parse correction with natural language feedback, proposing a new solution built on the success of autoregressive decoders in text-to-SQL tasks. By separating the semantic and syntactic difficulties of the task, we show that the accuracy of text-to-SQL parsers can be boosted by up to 26% with only one turn of correction with natural language. Additionally, we show that a T5-base model is capable of correcting the errors of a T5-large model in a zero-shot, cross-parser setting.
%R 10.18653/v1/2023.nlp4convai-1.3
%U https://aclanthology.org/2023.nlp4convai-1.3
%U https://doi.org/10.18653/v1/2023.nlp4convai-1.3
%P 29-38
Markdown (Informal)
[Correcting Semantic Parses with Natural Language through Dynamic Schema Encoding](https://aclanthology.org/2023.nlp4convai-1.3) (Glenn et al., NLP4ConvAI 2023)
ACL