@inproceedings{jwalapuram-etal-2020-pronoun,
title = "Pronoun-Targeted Fine-tuning for {NMT} with Hybrid Losses",
author = "Jwalapuram, Prathyusha and
Joty, Shafiq and
Shen, Youlin",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.177",
doi = "10.18653/v1/2020.emnlp-main.177",
pages = "2267--2279",
abstract = "Popular Neural Machine Translation model training uses strategies like backtranslation to improve BLEU scores, requiring large amounts of additional data and training. We introduce a class of conditional generative-discriminative hybrid losses that we use to fine-tune a trained machine translation model. Through a combination of targeted fine-tuning objectives and intuitive re-use of the training data the model has failed to adequately learn from, we improve the model performance of both a sentence-level and a contextual model without using any additional data. We target the improvement of pronoun translations through our fine-tuning and evaluate our models on a pronoun benchmark testset. Our sentence-level model shows a 0.5 BLEU improvement on both the WMT14 and the IWSLT13 De-En testsets, while our contextual model achieves the best results, improving from 31.81 to 32 BLEU on WMT14 De-En testset, and from 32.10 to 33.13 on the IWSLT13 De-En testset, with corresponding improvements in pronoun translation. We further show the generalizability of our method by reproducing the improvements on two additional language pairs, Fr-En and Cs-En.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jwalapuram-etal-2020-pronoun">
<titleInfo>
<title>Pronoun-Targeted Fine-tuning for NMT with Hybrid Losses</title>
</titleInfo>
<name type="personal">
<namePart type="given">Prathyusha</namePart>
<namePart type="family">Jwalapuram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shafiq</namePart>
<namePart type="family">Joty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youlin</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>Popular Neural Machine Translation model training uses strategies like backtranslation to improve BLEU scores, requiring large amounts of additional data and training. We introduce a class of conditional generative-discriminative hybrid losses that we use to fine-tune a trained machine translation model. Through a combination of targeted fine-tuning objectives and intuitive re-use of the training data the model has failed to adequately learn from, we improve the model performance of both a sentence-level and a contextual model without using any additional data. We target the improvement of pronoun translations through our fine-tuning and evaluate our models on a pronoun benchmark testset. Our sentence-level model shows a 0.5 BLEU improvement on both the WMT14 and the IWSLT13 De-En testsets, while our contextual model achieves the best results, improving from 31.81 to 32 BLEU on WMT14 De-En testset, and from 32.10 to 33.13 on the IWSLT13 De-En testset, with corresponding improvements in pronoun translation. We further show the generalizability of our method by reproducing the improvements on two additional language pairs, Fr-En and Cs-En.</abstract>
<identifier type="citekey">jwalapuram-etal-2020-pronoun</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.177</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.177</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>2267</start>
<end>2279</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pronoun-Targeted Fine-tuning for NMT with Hybrid Losses
%A Jwalapuram, Prathyusha
%A Joty, Shafiq
%A Shen, Youlin
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F jwalapuram-etal-2020-pronoun
%X Popular Neural Machine Translation model training uses strategies like backtranslation to improve BLEU scores, requiring large amounts of additional data and training. We introduce a class of conditional generative-discriminative hybrid losses that we use to fine-tune a trained machine translation model. Through a combination of targeted fine-tuning objectives and intuitive re-use of the training data the model has failed to adequately learn from, we improve the model performance of both a sentence-level and a contextual model without using any additional data. We target the improvement of pronoun translations through our fine-tuning and evaluate our models on a pronoun benchmark testset. Our sentence-level model shows a 0.5 BLEU improvement on both the WMT14 and the IWSLT13 De-En testsets, while our contextual model achieves the best results, improving from 31.81 to 32 BLEU on WMT14 De-En testset, and from 32.10 to 33.13 on the IWSLT13 De-En testset, with corresponding improvements in pronoun translation. We further show the generalizability of our method by reproducing the improvements on two additional language pairs, Fr-En and Cs-En.
%R 10.18653/v1/2020.emnlp-main.177
%U https://aclanthology.org/2020.emnlp-main.177
%U https://doi.org/10.18653/v1/2020.emnlp-main.177
%P 2267-2279
Markdown (Informal)
[Pronoun-Targeted Fine-tuning for NMT with Hybrid Losses](https://aclanthology.org/2020.emnlp-main.177) (Jwalapuram et al., EMNLP 2020)
ACL
- Prathyusha Jwalapuram, Shafiq Joty, and Youlin Shen. 2020. Pronoun-Targeted Fine-tuning for NMT with Hybrid Losses. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2267–2279, Online. Association for Computational Linguistics.