@inproceedings{li-etal-2023-best,
title = "The Best of Both Worlds: Combining Human and Machine Translations for Multilingual Semantic Parsing with Active Learning",
author = "Li, Zhuang and
Qu, Lizhen and
Cohen, Philip and
Tumuluri, Raj and
Haffari, Gholamreza",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.529/",
doi = "10.18653/v1/2023.acl-long.529",
pages = "9511--9528",
abstract = "Multilingual semantic parsing aims to leverage the knowledge from the high-resource languages to improve low-resource semantic parsing, yet commonly suffers from the data imbalance problem. Prior works propose to utilize the translations by either humans or machines to alleviate such issues. However, human translations are expensive, while machine translations are cheap but prone to error and bias. In this work, we propose an active learning approach that exploits the strengths of both human and machine translations by iteratively adding small batches of human translations into the machine-translated training set. Besides, we propose novel aggregated acquisition criteria that help our active learning method select utterances to be manually translated. Our experiments demonstrate that an ideal utterance selection can significantly reduce the error and bias in the translated data, resulting in higher parser accuracies than the parsers merely trained on the machine-translated data."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2023-best">
<titleInfo>
<title>The Best of Both Worlds: Combining Human and Machine Translations for Multilingual Semantic Parsing with Active Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhuang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lizhen</namePart>
<namePart type="family">Qu</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">Raj</namePart>
<namePart type="family">Tumuluri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multilingual semantic parsing aims to leverage the knowledge from the high-resource languages to improve low-resource semantic parsing, yet commonly suffers from the data imbalance problem. Prior works propose to utilize the translations by either humans or machines to alleviate such issues. However, human translations are expensive, while machine translations are cheap but prone to error and bias. In this work, we propose an active learning approach that exploits the strengths of both human and machine translations by iteratively adding small batches of human translations into the machine-translated training set. Besides, we propose novel aggregated acquisition criteria that help our active learning method select utterances to be manually translated. Our experiments demonstrate that an ideal utterance selection can significantly reduce the error and bias in the translated data, resulting in higher parser accuracies than the parsers merely trained on the machine-translated data.</abstract>
<identifier type="citekey">li-etal-2023-best</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.529</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.529/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>9511</start>
<end>9528</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Best of Both Worlds: Combining Human and Machine Translations for Multilingual Semantic Parsing with Active Learning
%A Li, Zhuang
%A Qu, Lizhen
%A Cohen, Philip
%A Tumuluri, Raj
%A Haffari, Gholamreza
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F li-etal-2023-best
%X Multilingual semantic parsing aims to leverage the knowledge from the high-resource languages to improve low-resource semantic parsing, yet commonly suffers from the data imbalance problem. Prior works propose to utilize the translations by either humans or machines to alleviate such issues. However, human translations are expensive, while machine translations are cheap but prone to error and bias. In this work, we propose an active learning approach that exploits the strengths of both human and machine translations by iteratively adding small batches of human translations into the machine-translated training set. Besides, we propose novel aggregated acquisition criteria that help our active learning method select utterances to be manually translated. Our experiments demonstrate that an ideal utterance selection can significantly reduce the error and bias in the translated data, resulting in higher parser accuracies than the parsers merely trained on the machine-translated data.
%R 10.18653/v1/2023.acl-long.529
%U https://aclanthology.org/2023.acl-long.529/
%U https://doi.org/10.18653/v1/2023.acl-long.529
%P 9511-9528
Markdown (Informal)
[The Best of Both Worlds: Combining Human and Machine Translations for Multilingual Semantic Parsing with Active Learning](https://aclanthology.org/2023.acl-long.529/) (Li et al., ACL 2023)
ACL