@inproceedings{dasigi-etal-2019-iterative,
title = "Iterative Search for Weakly Supervised Semantic Parsing",
author = "Dasigi, Pradeep and
Gardner, Matt and
Murty, Shikhar and
Zettlemoyer, Luke and
Hovy, Eduard",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1273",
doi = "10.18653/v1/N19-1273",
pages = "2669--2680",
abstract = "Training semantic parsers from question-answer pairs typically involves searching over an exponentially large space of logical forms, and an unguided search can easily be misled by spurious logical forms that coincidentally evaluate to the correct answer. We propose a novel iterative training algorithm that alternates between searching for consistent logical forms and maximizing the marginal likelihood of the retrieved ones. This training scheme lets us iteratively train models that provide guidance to subsequent ones to search for logical forms of increasing complexity, thus dealing with the problem of spuriousness. We evaluate these techniques on two hard datasets: WikiTableQuestions (WTQ) and Cornell Natural Language Visual Reasoning (NLVR), and show that our training algorithm outperforms the previous best systems, on WTQ in a comparable setting, and on NLVR with significantly less supervision.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dasigi-etal-2019-iterative">
<titleInfo>
<title>Iterative Search for Weakly Supervised Semantic Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pradeep</namePart>
<namePart type="family">Dasigi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matt</namePart>
<namePart type="family">Gardner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shikhar</namePart>
<namePart type="family">Murty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduard</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Training semantic parsers from question-answer pairs typically involves searching over an exponentially large space of logical forms, and an unguided search can easily be misled by spurious logical forms that coincidentally evaluate to the correct answer. We propose a novel iterative training algorithm that alternates between searching for consistent logical forms and maximizing the marginal likelihood of the retrieved ones. This training scheme lets us iteratively train models that provide guidance to subsequent ones to search for logical forms of increasing complexity, thus dealing with the problem of spuriousness. We evaluate these techniques on two hard datasets: WikiTableQuestions (WTQ) and Cornell Natural Language Visual Reasoning (NLVR), and show that our training algorithm outperforms the previous best systems, on WTQ in a comparable setting, and on NLVR with significantly less supervision.</abstract>
<identifier type="citekey">dasigi-etal-2019-iterative</identifier>
<identifier type="doi">10.18653/v1/N19-1273</identifier>
<location>
<url>https://aclanthology.org/N19-1273</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>2669</start>
<end>2680</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Iterative Search for Weakly Supervised Semantic Parsing
%A Dasigi, Pradeep
%A Gardner, Matt
%A Murty, Shikhar
%A Zettlemoyer, Luke
%A Hovy, Eduard
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F dasigi-etal-2019-iterative
%X Training semantic parsers from question-answer pairs typically involves searching over an exponentially large space of logical forms, and an unguided search can easily be misled by spurious logical forms that coincidentally evaluate to the correct answer. We propose a novel iterative training algorithm that alternates between searching for consistent logical forms and maximizing the marginal likelihood of the retrieved ones. This training scheme lets us iteratively train models that provide guidance to subsequent ones to search for logical forms of increasing complexity, thus dealing with the problem of spuriousness. We evaluate these techniques on two hard datasets: WikiTableQuestions (WTQ) and Cornell Natural Language Visual Reasoning (NLVR), and show that our training algorithm outperforms the previous best systems, on WTQ in a comparable setting, and on NLVR with significantly less supervision.
%R 10.18653/v1/N19-1273
%U https://aclanthology.org/N19-1273
%U https://doi.org/10.18653/v1/N19-1273
%P 2669-2680
Markdown (Informal)
[Iterative Search for Weakly Supervised Semantic Parsing](https://aclanthology.org/N19-1273) (Dasigi et al., NAACL 2019)
ACL
- Pradeep Dasigi, Matt Gardner, Shikhar Murty, Luke Zettlemoyer, and Eduard Hovy. 2019. Iterative Search for Weakly Supervised Semantic Parsing. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2669–2680, Minneapolis, Minnesota. Association for Computational Linguistics.