@inproceedings{ravichander-etal-2017-say,
title = "How Would You Say It? Eliciting Lexically Diverse Dialogue for Supervised Semantic Parsing",
author = "Ravichander, Abhilasha and
Manzini, Thomas and
Grabmair, Matthias and
Neubig, Graham and
Francis, Jonathan and
Nyberg, Eric",
editor = "Jokinen, Kristiina and
Stede, Manfred and
DeVault, David and
Louis, Annie",
booktitle = "Proceedings of the 18th Annual {SIG}dial Meeting on Discourse and Dialogue",
month = aug,
year = "2017",
address = {Saarbr{\"u}cken, Germany},
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-5545",
doi = "10.18653/v1/W17-5545",
pages = "374--383",
abstract = "Building dialogue interfaces for real-world scenarios often entails training semantic parsers starting from zero examples. How can we build datasets that better capture the variety of ways users might phrase their queries, and what queries are actually realistic? Wang et al. (2015) proposed a method to build semantic parsing datasets by generating canonical utterances using a grammar and having crowdworkers paraphrase them into natural wording. A limitation of this approach is that it induces bias towards using similar language as the canonical utterances. In this work, we present a methodology that elicits meaningful and lexically diverse queries from users for semantic parsing tasks. Starting from a seed lexicon and a generative grammar, we pair logical forms with mixed text-image representations and ask crowdworkers to paraphrase and confirm the plausibility of the queries that they generated. We use this method to build a semantic parsing dataset from scratch for a dialog agent in a smart-home simulation. We find evidence that this dataset, which we have named SmartHome, is demonstrably more lexically diverse and difficult to parse than existing domain-specific semantic parsing datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ravichander-etal-2017-say">
<titleInfo>
<title>How Would You Say It? Eliciting Lexically Diverse Dialogue for Supervised Semantic Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abhilasha</namePart>
<namePart type="family">Ravichander</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Manzini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Grabmair</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Francis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Nyberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristiina</namePart>
<namePart type="family">Jokinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manfred</namePart>
<namePart type="family">Stede</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">DeVault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annie</namePart>
<namePart type="family">Louis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Saarbrücken, Germany</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Building dialogue interfaces for real-world scenarios often entails training semantic parsers starting from zero examples. How can we build datasets that better capture the variety of ways users might phrase their queries, and what queries are actually realistic? Wang et al. (2015) proposed a method to build semantic parsing datasets by generating canonical utterances using a grammar and having crowdworkers paraphrase them into natural wording. A limitation of this approach is that it induces bias towards using similar language as the canonical utterances. In this work, we present a methodology that elicits meaningful and lexically diverse queries from users for semantic parsing tasks. Starting from a seed lexicon and a generative grammar, we pair logical forms with mixed text-image representations and ask crowdworkers to paraphrase and confirm the plausibility of the queries that they generated. We use this method to build a semantic parsing dataset from scratch for a dialog agent in a smart-home simulation. We find evidence that this dataset, which we have named SmartHome, is demonstrably more lexically diverse and difficult to parse than existing domain-specific semantic parsing datasets.</abstract>
<identifier type="citekey">ravichander-etal-2017-say</identifier>
<identifier type="doi">10.18653/v1/W17-5545</identifier>
<location>
<url>https://aclanthology.org/W17-5545</url>
</location>
<part>
<date>2017-08</date>
<extent unit="page">
<start>374</start>
<end>383</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Would You Say It? Eliciting Lexically Diverse Dialogue for Supervised Semantic Parsing
%A Ravichander, Abhilasha
%A Manzini, Thomas
%A Grabmair, Matthias
%A Neubig, Graham
%A Francis, Jonathan
%A Nyberg, Eric
%Y Jokinen, Kristiina
%Y Stede, Manfred
%Y DeVault, David
%Y Louis, Annie
%S Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue
%D 2017
%8 August
%I Association for Computational Linguistics
%C Saarbrücken, Germany
%F ravichander-etal-2017-say
%X Building dialogue interfaces for real-world scenarios often entails training semantic parsers starting from zero examples. How can we build datasets that better capture the variety of ways users might phrase their queries, and what queries are actually realistic? Wang et al. (2015) proposed a method to build semantic parsing datasets by generating canonical utterances using a grammar and having crowdworkers paraphrase them into natural wording. A limitation of this approach is that it induces bias towards using similar language as the canonical utterances. In this work, we present a methodology that elicits meaningful and lexically diverse queries from users for semantic parsing tasks. Starting from a seed lexicon and a generative grammar, we pair logical forms with mixed text-image representations and ask crowdworkers to paraphrase and confirm the plausibility of the queries that they generated. We use this method to build a semantic parsing dataset from scratch for a dialog agent in a smart-home simulation. We find evidence that this dataset, which we have named SmartHome, is demonstrably more lexically diverse and difficult to parse than existing domain-specific semantic parsing datasets.
%R 10.18653/v1/W17-5545
%U https://aclanthology.org/W17-5545
%U https://doi.org/10.18653/v1/W17-5545
%P 374-383
Markdown (Informal)
[How Would You Say It? Eliciting Lexically Diverse Dialogue for Supervised Semantic Parsing](https://aclanthology.org/W17-5545) (Ravichander et al., SIGDIAL 2017)
ACL