@inproceedings{bhatnagar-etal-2021-dont,
title = "Don{'}t Rule Out Monolingual Speakers: {A} Method For Crowdsourcing Machine Translation Data",
author = "Bhatnagar, Rajat and
Ganesh, Ananya and
Kann, Katharina",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.139",
doi = "10.18653/v1/2021.acl-short.139",
pages = "1099--1106",
abstract = "High-performing machine translation (MT) systems can help overcome language barriers while making it possible for everyone to communicate and use language technologies in the language of their choice. However, such systems require large amounts of parallel sentences for training, and translators can be difficult to find and expensive. Here, we present a data collection strategy for MT which, in contrast, is cheap and simple, as it does not require bilingual speakers. Based on the insight that humans pay specific attention to movements, we use graphics interchange formats (GIFs) as a pivot to collect parallel sentences from monolingual annotators. We use our strategy to collect data in Hindi, Tamil and English. As a baseline, we also collect data using images as a pivot. We perform an intrinsic evaluation by manually evaluating a subset of the sentence pairs and an extrinsic evaluation by finetuning mBART (Liu et al., 2020) on the collected data. We find that sentences collected via GIFs are indeed of higher quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhatnagar-etal-2021-dont">
<titleInfo>
<title>Don’t Rule Out Monolingual Speakers: A Method For Crowdsourcing Machine Translation Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rajat</namePart>
<namePart type="family">Bhatnagar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ananya</namePart>
<namePart type="family">Ganesh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Kann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>High-performing machine translation (MT) systems can help overcome language barriers while making it possible for everyone to communicate and use language technologies in the language of their choice. However, such systems require large amounts of parallel sentences for training, and translators can be difficult to find and expensive. Here, we present a data collection strategy for MT which, in contrast, is cheap and simple, as it does not require bilingual speakers. Based on the insight that humans pay specific attention to movements, we use graphics interchange formats (GIFs) as a pivot to collect parallel sentences from monolingual annotators. We use our strategy to collect data in Hindi, Tamil and English. As a baseline, we also collect data using images as a pivot. We perform an intrinsic evaluation by manually evaluating a subset of the sentence pairs and an extrinsic evaluation by finetuning mBART (Liu et al., 2020) on the collected data. We find that sentences collected via GIFs are indeed of higher quality.</abstract>
<identifier type="citekey">bhatnagar-etal-2021-dont</identifier>
<identifier type="doi">10.18653/v1/2021.acl-short.139</identifier>
<location>
<url>https://aclanthology.org/2021.acl-short.139</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>1099</start>
<end>1106</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Don’t Rule Out Monolingual Speakers: A Method For Crowdsourcing Machine Translation Data
%A Bhatnagar, Rajat
%A Ganesh, Ananya
%A Kann, Katharina
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F bhatnagar-etal-2021-dont
%X High-performing machine translation (MT) systems can help overcome language barriers while making it possible for everyone to communicate and use language technologies in the language of their choice. However, such systems require large amounts of parallel sentences for training, and translators can be difficult to find and expensive. Here, we present a data collection strategy for MT which, in contrast, is cheap and simple, as it does not require bilingual speakers. Based on the insight that humans pay specific attention to movements, we use graphics interchange formats (GIFs) as a pivot to collect parallel sentences from monolingual annotators. We use our strategy to collect data in Hindi, Tamil and English. As a baseline, we also collect data using images as a pivot. We perform an intrinsic evaluation by manually evaluating a subset of the sentence pairs and an extrinsic evaluation by finetuning mBART (Liu et al., 2020) on the collected data. We find that sentences collected via GIFs are indeed of higher quality.
%R 10.18653/v1/2021.acl-short.139
%U https://aclanthology.org/2021.acl-short.139
%U https://doi.org/10.18653/v1/2021.acl-short.139
%P 1099-1106
Markdown (Informal)
[Don’t Rule Out Monolingual Speakers: A Method For Crowdsourcing Machine Translation Data](https://aclanthology.org/2021.acl-short.139) (Bhatnagar et al., ACL-IJCNLP 2021)
ACL