@inproceedings{xu-etal-2020-autoqa,
title = "{A}uto{QA}: From Databases To {QA} Semantic Parsers With Only Synthetic Training Data",
author = "Xu, Silei and
Semnani, Sina and
Campagna, Giovanni and
Lam, Monica",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.31",
doi = "10.18653/v1/2020.emnlp-main.31",
pages = "422--434",
abstract = "We propose AutoQA, a methodology and toolkit to generate semantic parsers that answer questions on databases, with no manual effort. Given a database schema and its data, AutoQA automatically generates a large set of high-quality questions for training that covers different database operations. It uses automatic paraphrasing combined with template-based parsing to find alternative expressions of an attribute in different parts of speech. It also uses a novel filtered auto-paraphraser to generate correct paraphrases of entire sentences. We apply AutoQA to the Schema2QA dataset and obtain an average logical form accuracy of 62.9{\%} when tested on natural questions, which is only 6.4{\%} lower than a model trained with expert natural language annotations and paraphrase data collected from crowdworkers. To demonstrate the generality of AutoQA, we also apply it to the Overnight dataset. AutoQA achieves 69.8{\%} answer accuracy, 16.4{\%} higher than the state-of-the-art zero-shot models and only 5.2{\%} lower than the same model trained with human data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2020-autoqa">
<titleInfo>
<title>AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Silei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Semnani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Campagna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monica</namePart>
<namePart type="family">Lam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose AutoQA, a methodology and toolkit to generate semantic parsers that answer questions on databases, with no manual effort. Given a database schema and its data, AutoQA automatically generates a large set of high-quality questions for training that covers different database operations. It uses automatic paraphrasing combined with template-based parsing to find alternative expressions of an attribute in different parts of speech. It also uses a novel filtered auto-paraphraser to generate correct paraphrases of entire sentences. We apply AutoQA to the Schema2QA dataset and obtain an average logical form accuracy of 62.9% when tested on natural questions, which is only 6.4% lower than a model trained with expert natural language annotations and paraphrase data collected from crowdworkers. To demonstrate the generality of AutoQA, we also apply it to the Overnight dataset. AutoQA achieves 69.8% answer accuracy, 16.4% higher than the state-of-the-art zero-shot models and only 5.2% lower than the same model trained with human data.</abstract>
<identifier type="citekey">xu-etal-2020-autoqa</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.31</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.31</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>422</start>
<end>434</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data
%A Xu, Silei
%A Semnani, Sina
%A Campagna, Giovanni
%A Lam, Monica
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F xu-etal-2020-autoqa
%X We propose AutoQA, a methodology and toolkit to generate semantic parsers that answer questions on databases, with no manual effort. Given a database schema and its data, AutoQA automatically generates a large set of high-quality questions for training that covers different database operations. It uses automatic paraphrasing combined with template-based parsing to find alternative expressions of an attribute in different parts of speech. It also uses a novel filtered auto-paraphraser to generate correct paraphrases of entire sentences. We apply AutoQA to the Schema2QA dataset and obtain an average logical form accuracy of 62.9% when tested on natural questions, which is only 6.4% lower than a model trained with expert natural language annotations and paraphrase data collected from crowdworkers. To demonstrate the generality of AutoQA, we also apply it to the Overnight dataset. AutoQA achieves 69.8% answer accuracy, 16.4% higher than the state-of-the-art zero-shot models and only 5.2% lower than the same model trained with human data.
%R 10.18653/v1/2020.emnlp-main.31
%U https://aclanthology.org/2020.emnlp-main.31
%U https://doi.org/10.18653/v1/2020.emnlp-main.31
%P 422-434
Markdown (Informal)
[AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data](https://aclanthology.org/2020.emnlp-main.31) (Xu et al., EMNLP 2020)
ACL