@inproceedings{nicosia-etal-2021-translate-fill,
title = "{T}ranslate {\&} {F}ill: {I}mproving Zero-Shot Multilingual Semantic Parsing with Synthetic Data",
author = "Nicosia, Massimo and
Qu, Zhongdi and
Altun, Yasemin",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.279",
doi = "10.18653/v1/2021.findings-emnlp.279",
pages = "3272--3284",
abstract = "While multilingual pretrained language models (LMs) fine-tuned on a single language have shown substantial cross-lingual task transfer capabilities, there is still a wide performance gap in semantic parsing tasks when target language supervision is available. In this paper, we propose a novel Translate-and-Fill (TaF) method to produce silver training data for a multilingual semantic parser. This method simplifies the popular Translate-Align-Project (TAP) pipeline and consists of a sequence-to-sequence filler model that constructs a full parse conditioned on an utterance and a view of the same parse. Our filler is trained on English data only but can accurately complete instances in other languages (i.e., translations of the English training utterances), in a zero-shot fashion. Experimental results on three multilingual semantic parsing datasets show that data augmentation with TaF reaches accuracies competitive with similar systems which rely on traditional alignment techniques.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nicosia-etal-2021-translate-fill">
<titleInfo>
<title>Translate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Massimo</namePart>
<namePart type="family">Nicosia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongdi</namePart>
<namePart type="family">Qu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasemin</namePart>
<namePart type="family">Altun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</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>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While multilingual pretrained language models (LMs) fine-tuned on a single language have shown substantial cross-lingual task transfer capabilities, there is still a wide performance gap in semantic parsing tasks when target language supervision is available. In this paper, we propose a novel Translate-and-Fill (TaF) method to produce silver training data for a multilingual semantic parser. This method simplifies the popular Translate-Align-Project (TAP) pipeline and consists of a sequence-to-sequence filler model that constructs a full parse conditioned on an utterance and a view of the same parse. Our filler is trained on English data only but can accurately complete instances in other languages (i.e., translations of the English training utterances), in a zero-shot fashion. Experimental results on three multilingual semantic parsing datasets show that data augmentation with TaF reaches accuracies competitive with similar systems which rely on traditional alignment techniques.</abstract>
<identifier type="citekey">nicosia-etal-2021-translate-fill</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.279</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.279</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>3272</start>
<end>3284</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Translate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Data
%A Nicosia, Massimo
%A Qu, Zhongdi
%A Altun, Yasemin
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F nicosia-etal-2021-translate-fill
%X While multilingual pretrained language models (LMs) fine-tuned on a single language have shown substantial cross-lingual task transfer capabilities, there is still a wide performance gap in semantic parsing tasks when target language supervision is available. In this paper, we propose a novel Translate-and-Fill (TaF) method to produce silver training data for a multilingual semantic parser. This method simplifies the popular Translate-Align-Project (TAP) pipeline and consists of a sequence-to-sequence filler model that constructs a full parse conditioned on an utterance and a view of the same parse. Our filler is trained on English data only but can accurately complete instances in other languages (i.e., translations of the English training utterances), in a zero-shot fashion. Experimental results on three multilingual semantic parsing datasets show that data augmentation with TaF reaches accuracies competitive with similar systems which rely on traditional alignment techniques.
%R 10.18653/v1/2021.findings-emnlp.279
%U https://aclanthology.org/2021.findings-emnlp.279
%U https://doi.org/10.18653/v1/2021.findings-emnlp.279
%P 3272-3284
Markdown (Informal)
[Translate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Data](https://aclanthology.org/2021.findings-emnlp.279) (Nicosia et al., Findings 2021)
ACL