@inproceedings{duong-etal-2017-multilingual-semantic,
title = "Multilingual Semantic Parsing And Code-Switching",
author = "Duong, Long and
Afshar, Hadi and
Estival, Dominique and
Pink, Glen and
Cohen, Philip and
Johnson, Mark",
editor = "Levy, Roger and
Specia, Lucia",
booktitle = "Proceedings of the 21st Conference on Computational Natural Language Learning ({C}o{NLL} 2017)",
month = aug,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/K17-1038/",
doi = "10.18653/v1/K17-1038",
pages = "379--389",
abstract = "Extending semantic parsing systems to new domains and languages is a highly expensive, time-consuming process, so making effective use of existing resources is critical. In this paper, we describe a transfer learning method using crosslingual word embeddings in a sequence-to-sequence model. On the NLmaps corpus, our approach achieves state-of-the-art accuracy of 85.7{\%} for English. Most importantly, we observed a consistent improvement for German compared with several baseline domain adaptation techniques. As a by-product of this approach, our models that are trained on a combination of English and German utterances perform reasonably well on code-switching utterances which contain a mixture of English and German, even though the training data does not contain any such. As far as we know, this is the first study of code-switching in semantic parsing. We manually constructed the set of code-switching test utterances for the NLmaps corpus and achieve 78.3{\%} accuracy on this dataset."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="duong-etal-2017-multilingual-semantic">
<titleInfo>
<title>Multilingual Semantic Parsing And Code-Switching</title>
</titleInfo>
<name type="personal">
<namePart type="given">Long</namePart>
<namePart type="family">Duong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hadi</namePart>
<namePart type="family">Afshar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dominique</namePart>
<namePart type="family">Estival</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Glen</namePart>
<namePart type="family">Pink</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philip</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Johnson</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 21st Conference on Computational Natural Language Learning (CoNLL 2017)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Roger</namePart>
<namePart type="family">Levy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Extending semantic parsing systems to new domains and languages is a highly expensive, time-consuming process, so making effective use of existing resources is critical. In this paper, we describe a transfer learning method using crosslingual word embeddings in a sequence-to-sequence model. On the NLmaps corpus, our approach achieves state-of-the-art accuracy of 85.7% for English. Most importantly, we observed a consistent improvement for German compared with several baseline domain adaptation techniques. As a by-product of this approach, our models that are trained on a combination of English and German utterances perform reasonably well on code-switching utterances which contain a mixture of English and German, even though the training data does not contain any such. As far as we know, this is the first study of code-switching in semantic parsing. We manually constructed the set of code-switching test utterances for the NLmaps corpus and achieve 78.3% accuracy on this dataset.</abstract>
<identifier type="citekey">duong-etal-2017-multilingual-semantic</identifier>
<identifier type="doi">10.18653/v1/K17-1038</identifier>
<location>
<url>https://aclanthology.org/K17-1038/</url>
</location>
<part>
<date>2017-08</date>
<extent unit="page">
<start>379</start>
<end>389</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual Semantic Parsing And Code-Switching
%A Duong, Long
%A Afshar, Hadi
%A Estival, Dominique
%A Pink, Glen
%A Cohen, Philip
%A Johnson, Mark
%Y Levy, Roger
%Y Specia, Lucia
%S Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)
%D 2017
%8 August
%I Association for Computational Linguistics
%C Vancouver, Canada
%F duong-etal-2017-multilingual-semantic
%X Extending semantic parsing systems to new domains and languages is a highly expensive, time-consuming process, so making effective use of existing resources is critical. In this paper, we describe a transfer learning method using crosslingual word embeddings in a sequence-to-sequence model. On the NLmaps corpus, our approach achieves state-of-the-art accuracy of 85.7% for English. Most importantly, we observed a consistent improvement for German compared with several baseline domain adaptation techniques. As a by-product of this approach, our models that are trained on a combination of English and German utterances perform reasonably well on code-switching utterances which contain a mixture of English and German, even though the training data does not contain any such. As far as we know, this is the first study of code-switching in semantic parsing. We manually constructed the set of code-switching test utterances for the NLmaps corpus and achieve 78.3% accuracy on this dataset.
%R 10.18653/v1/K17-1038
%U https://aclanthology.org/K17-1038/
%U https://doi.org/10.18653/v1/K17-1038
%P 379-389
Markdown (Informal)
[Multilingual Semantic Parsing And Code-Switching](https://aclanthology.org/K17-1038/) (Duong et al., CoNLL 2017)
ACL
- Long Duong, Hadi Afshar, Dominique Estival, Glen Pink, Philip Cohen, and Mark Johnson. 2017. Multilingual Semantic Parsing And Code-Switching. In Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pages 379–389, Vancouver, Canada. Association for Computational Linguistics.