@inproceedings{choubey-etal-2021-gfst,
title = "{GFST}: {G}ender-Filtered Self-Training for More Accurate Gender in Translation",
author = "Choubey, Prafulla Kumar and
Currey, Anna and
Mathur, Prashant and
Dinu, Georgiana",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.123",
doi = "10.18653/v1/2021.emnlp-main.123",
pages = "1640--1654",
abstract = "Targeted evaluations have found that machine translation systems often output incorrect gender in translations, even when the gender is clear from context. Furthermore, these incorrectly gendered translations have the potential to reflect or amplify social biases. We propose gender-filtered self-training (GFST) to improve gender translation accuracy on unambiguously gendered inputs. Our GFST approach uses a source monolingual corpus and an initial model to generate gender-specific pseudo-parallel corpora which are then filtered and added to the training data. We evaluate GFST on translation from English into five languages, finding that it improves gender accuracy without damaging generic quality. We also show the viability of GFST on several experimental settings, including re-training from scratch, fine-tuning, controlling the gender balance of the data, forward translation, and back-translation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="choubey-etal-2021-gfst">
<titleInfo>
<title>GFST: Gender-Filtered Self-Training for More Accurate Gender in Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Prafulla</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Choubey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Currey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prashant</namePart>
<namePart type="family">Mathur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georgiana</namePart>
<namePart type="family">Dinu</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>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</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">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Targeted evaluations have found that machine translation systems often output incorrect gender in translations, even when the gender is clear from context. Furthermore, these incorrectly gendered translations have the potential to reflect or amplify social biases. We propose gender-filtered self-training (GFST) to improve gender translation accuracy on unambiguously gendered inputs. Our GFST approach uses a source monolingual corpus and an initial model to generate gender-specific pseudo-parallel corpora which are then filtered and added to the training data. We evaluate GFST on translation from English into five languages, finding that it improves gender accuracy without damaging generic quality. We also show the viability of GFST on several experimental settings, including re-training from scratch, fine-tuning, controlling the gender balance of the data, forward translation, and back-translation.</abstract>
<identifier type="citekey">choubey-etal-2021-gfst</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.123</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.123</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>1640</start>
<end>1654</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GFST: Gender-Filtered Self-Training for More Accurate Gender in Translation
%A Choubey, Prafulla Kumar
%A Currey, Anna
%A Mathur, Prashant
%A Dinu, Georgiana
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F choubey-etal-2021-gfst
%X Targeted evaluations have found that machine translation systems often output incorrect gender in translations, even when the gender is clear from context. Furthermore, these incorrectly gendered translations have the potential to reflect or amplify social biases. We propose gender-filtered self-training (GFST) to improve gender translation accuracy on unambiguously gendered inputs. Our GFST approach uses a source monolingual corpus and an initial model to generate gender-specific pseudo-parallel corpora which are then filtered and added to the training data. We evaluate GFST on translation from English into five languages, finding that it improves gender accuracy without damaging generic quality. We also show the viability of GFST on several experimental settings, including re-training from scratch, fine-tuning, controlling the gender balance of the data, forward translation, and back-translation.
%R 10.18653/v1/2021.emnlp-main.123
%U https://aclanthology.org/2021.emnlp-main.123
%U https://doi.org/10.18653/v1/2021.emnlp-main.123
%P 1640-1654
Markdown (Informal)
[GFST: Gender-Filtered Self-Training for More Accurate Gender in Translation](https://aclanthology.org/2021.emnlp-main.123) (Choubey et al., EMNLP 2021)
ACL