@inproceedings{rubino-sumita-2020-intermediate,
title = "Intermediate Self-supervised Learning for Machine Translation Quality Estimation",
author = "Rubino, Raphael and
Sumita, Eiichiro",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.385",
doi = "10.18653/v1/2020.coling-main.385",
pages = "4355--4360",
abstract = "Pre-training sentence encoders is effective in many natural language processing tasks including machine translation (MT) quality estimation (QE), due partly to the scarcity of annotated QE data required for supervised learning. In this paper, we investigate the use of an intermediate self-supervised learning task for sentence encoder aiming at improving QE performances at the sentence and word levels. Our approach is motivated by a problem inherent to QE: mistakes in translation caused by wrongly inserted and deleted tokens. We modify the translation language model (TLM) training objective of the cross-lingual language model (XLM) to orientate the pre-trained model towards the target task. The proposed method does not rely on annotated data and is complementary to QE methods involving pre-trained sentence encoders and domain adaptation. Experiments on English-to-German and English-to-Russian translation directions show that intermediate learning improves over domain adaptated models. Additionally, our method reaches results in par with state-of-the-art QE models without requiring the combination of several approaches and outperforms similar methods based on pre-trained sentence encoders.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rubino-sumita-2020-intermediate">
<titleInfo>
<title>Intermediate Self-supervised Learning for Machine Translation Quality Estimation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raphael</namePart>
<namePart type="family">Rubino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiichiro</namePart>
<namePart type="family">Sumita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pre-training sentence encoders is effective in many natural language processing tasks including machine translation (MT) quality estimation (QE), due partly to the scarcity of annotated QE data required for supervised learning. In this paper, we investigate the use of an intermediate self-supervised learning task for sentence encoder aiming at improving QE performances at the sentence and word levels. Our approach is motivated by a problem inherent to QE: mistakes in translation caused by wrongly inserted and deleted tokens. We modify the translation language model (TLM) training objective of the cross-lingual language model (XLM) to orientate the pre-trained model towards the target task. The proposed method does not rely on annotated data and is complementary to QE methods involving pre-trained sentence encoders and domain adaptation. Experiments on English-to-German and English-to-Russian translation directions show that intermediate learning improves over domain adaptated models. Additionally, our method reaches results in par with state-of-the-art QE models without requiring the combination of several approaches and outperforms similar methods based on pre-trained sentence encoders.</abstract>
<identifier type="citekey">rubino-sumita-2020-intermediate</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.385</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.385</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>4355</start>
<end>4360</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Intermediate Self-supervised Learning for Machine Translation Quality Estimation
%A Rubino, Raphael
%A Sumita, Eiichiro
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F rubino-sumita-2020-intermediate
%X Pre-training sentence encoders is effective in many natural language processing tasks including machine translation (MT) quality estimation (QE), due partly to the scarcity of annotated QE data required for supervised learning. In this paper, we investigate the use of an intermediate self-supervised learning task for sentence encoder aiming at improving QE performances at the sentence and word levels. Our approach is motivated by a problem inherent to QE: mistakes in translation caused by wrongly inserted and deleted tokens. We modify the translation language model (TLM) training objective of the cross-lingual language model (XLM) to orientate the pre-trained model towards the target task. The proposed method does not rely on annotated data and is complementary to QE methods involving pre-trained sentence encoders and domain adaptation. Experiments on English-to-German and English-to-Russian translation directions show that intermediate learning improves over domain adaptated models. Additionally, our method reaches results in par with state-of-the-art QE models without requiring the combination of several approaches and outperforms similar methods based on pre-trained sentence encoders.
%R 10.18653/v1/2020.coling-main.385
%U https://aclanthology.org/2020.coling-main.385
%U https://doi.org/10.18653/v1/2020.coling-main.385
%P 4355-4360
Markdown (Informal)
[Intermediate Self-supervised Learning for Machine Translation Quality Estimation](https://aclanthology.org/2020.coling-main.385) (Rubino & Sumita, COLING 2020)
ACL