@inproceedings{berger-etal-2023-enhancing,
title = "Enhancing Supervised Learning with Contrastive Markings in Neural Machine Translation Training",
author = "Berger, Nathaniel and
Exel, Miriam and
Huck, Matthias and
Riezler, Stefan",
editor = "Nurminen, Mary and
Brenner, Judith and
Koponen, Maarit and
Latomaa, Sirkku and
Mikhailov, Mikhail and
Schierl, Frederike and
Ranasinghe, Tharindu and
Vanmassenhove, Eva and
Vidal, Sergi Alvarez and
Aranberri, Nora and
Nunziatini, Mara and
Escart{\'\i}n, Carla Parra and
Forcada, Mikel and
Popovic, Maja and
Scarton, Carolina and
Moniz, Helena",
booktitle = "Proceedings of the 24th Annual Conference of the European Association for Machine Translation",
month = jun,
year = "2023",
address = "Tampere, Finland",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2023.eamt-1.8",
pages = "69--78",
abstract = "Supervised learning in Neural Machine Translation (NMT) standardly follows a teacher forcing paradigm where the conditioning context in the model{'}s prediction is constituted by reference tokens, instead of its own previous predictions. In order to alleviate this lack of exploration in the space of translations, we present a simple extension of standard maximum likelihood estimation by a contrastive marking objective. The additional training signals are extracted automatically from reference translations by comparing the system hypothesis against the reference, and used for up/down-weighting correct/incorrect tokens. The proposed new training procedure requires one additional translation pass over the training set, and does not alter the standard inference setup. We show that training with contrastive markings yields improvements on top of supervised learning, and is especially useful when learning from postedits where contrastive markings indicate human error corrections to the original hypotheses.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="berger-etal-2023-enhancing">
<titleInfo>
<title>Enhancing Supervised Learning with Contrastive Markings in Neural Machine Translation Training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Berger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miriam</namePart>
<namePart type="family">Exel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Huck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Riezler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Annual Conference of the European Association for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mary</namePart>
<namePart type="family">Nurminen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Judith</namePart>
<namePart type="family">Brenner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maarit</namePart>
<namePart type="family">Koponen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sirkku</namePart>
<namePart type="family">Latomaa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikhail</namePart>
<namePart type="family">Mikhailov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frederike</namePart>
<namePart type="family">Schierl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Vanmassenhove</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergi</namePart>
<namePart type="given">Alvarez</namePart>
<namePart type="family">Vidal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Aranberri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mara</namePart>
<namePart type="family">Nunziatini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carla</namePart>
<namePart type="given">Parra</namePart>
<namePart type="family">Escartín</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="family">Forcada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maja</namePart>
<namePart type="family">Popovic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolina</namePart>
<namePart type="family">Scarton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Tampere, Finland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Supervised learning in Neural Machine Translation (NMT) standardly follows a teacher forcing paradigm where the conditioning context in the model’s prediction is constituted by reference tokens, instead of its own previous predictions. In order to alleviate this lack of exploration in the space of translations, we present a simple extension of standard maximum likelihood estimation by a contrastive marking objective. The additional training signals are extracted automatically from reference translations by comparing the system hypothesis against the reference, and used for up/down-weighting correct/incorrect tokens. The proposed new training procedure requires one additional translation pass over the training set, and does not alter the standard inference setup. We show that training with contrastive markings yields improvements on top of supervised learning, and is especially useful when learning from postedits where contrastive markings indicate human error corrections to the original hypotheses.</abstract>
<identifier type="citekey">berger-etal-2023-enhancing</identifier>
<location>
<url>https://aclanthology.org/2023.eamt-1.8</url>
</location>
<part>
<date>2023-06</date>
<extent unit="page">
<start>69</start>
<end>78</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Supervised Learning with Contrastive Markings in Neural Machine Translation Training
%A Berger, Nathaniel
%A Exel, Miriam
%A Huck, Matthias
%A Riezler, Stefan
%Y Nurminen, Mary
%Y Brenner, Judith
%Y Koponen, Maarit
%Y Latomaa, Sirkku
%Y Mikhailov, Mikhail
%Y Schierl, Frederike
%Y Ranasinghe, Tharindu
%Y Vanmassenhove, Eva
%Y Vidal, Sergi Alvarez
%Y Aranberri, Nora
%Y Nunziatini, Mara
%Y Escartín, Carla Parra
%Y Forcada, Mikel
%Y Popovic, Maja
%Y Scarton, Carolina
%Y Moniz, Helena
%S Proceedings of the 24th Annual Conference of the European Association for Machine Translation
%D 2023
%8 June
%I European Association for Machine Translation
%C Tampere, Finland
%F berger-etal-2023-enhancing
%X Supervised learning in Neural Machine Translation (NMT) standardly follows a teacher forcing paradigm where the conditioning context in the model’s prediction is constituted by reference tokens, instead of its own previous predictions. In order to alleviate this lack of exploration in the space of translations, we present a simple extension of standard maximum likelihood estimation by a contrastive marking objective. The additional training signals are extracted automatically from reference translations by comparing the system hypothesis against the reference, and used for up/down-weighting correct/incorrect tokens. The proposed new training procedure requires one additional translation pass over the training set, and does not alter the standard inference setup. We show that training with contrastive markings yields improvements on top of supervised learning, and is especially useful when learning from postedits where contrastive markings indicate human error corrections to the original hypotheses.
%U https://aclanthology.org/2023.eamt-1.8
%P 69-78
Markdown (Informal)
[Enhancing Supervised Learning with Contrastive Markings in Neural Machine Translation Training](https://aclanthology.org/2023.eamt-1.8) (Berger et al., EAMT 2023)
ACL