@inproceedings{yang-etal-2020-efficient,
title = "Efficient Transfer Learning for Quality Estimation with Bottleneck Adapter Layer",
author = "Yang, Hao and
Wang, Minghan and
Xie, Ning and
Qin, Ying and
Deng, Yao",
editor = "Martins, Andr{\'e} and
Moniz, Helena and
Fumega, Sara and
Martins, Bruno and
Batista, Fernando and
Coheur, Luisa and
Parra, Carla and
Trancoso, Isabel and
Turchi, Marco and
Bisazza, Arianna and
Moorkens, Joss and
Guerberof, Ana and
Nurminen, Mary and
Marg, Lena and
Forcada, Mikel L.",
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.4",
pages = "29--34",
abstract = "The Predictor-Estimator framework for quality estimation (QE) is commonly used for its strong performance. Where the predictor and estimator works on feature extraction and quality evaluation, respectively. However, training the predictor from scratch is computationally expensive. In this paper, we propose an efficient transfer learning framework to transfer knowledge from NMT dataset into QE models. A Predictor-Estimator alike model named BAL-QE is also proposed, aiming to extract high quality features with pre-trained NMT model, and make classification with a fine-tuned Bottleneck Adapter Layer (BAL). The experiment shows that BAL-QE achieves 97{\%} of the SOTA performance in WMT19 En-De and En-Ru QE tasks by only training 3{\%} of parameters within 4 hours on 4 Titan XP GPUs. Compared with the commonly used NuQE baseline, BAL-QE achieves 47{\%} (En-Ru) and 75{\%} (En-De) of performance promotions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2020-efficient">
<titleInfo>
<title>Efficient Transfer Learning for Quality Estimation with Bottleneck Adapter Layer</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ning</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yao</namePart>
<namePart type="family">Deng</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 22nd Annual Conference of the European Association for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Martins</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>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Fumega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bruno</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="family">Batista</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luisa</namePart>
<namePart type="family">Coheur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carla</namePart>
<namePart type="family">Parra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabel</namePart>
<namePart type="family">Trancoso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arianna</namePart>
<namePart type="family">Bisazza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joss</namePart>
<namePart type="family">Moorkens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="family">Guerberof</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Lena</namePart>
<namePart type="family">Marg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Forcada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Lisboa, Portugal</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Predictor-Estimator framework for quality estimation (QE) is commonly used for its strong performance. Where the predictor and estimator works on feature extraction and quality evaluation, respectively. However, training the predictor from scratch is computationally expensive. In this paper, we propose an efficient transfer learning framework to transfer knowledge from NMT dataset into QE models. A Predictor-Estimator alike model named BAL-QE is also proposed, aiming to extract high quality features with pre-trained NMT model, and make classification with a fine-tuned Bottleneck Adapter Layer (BAL). The experiment shows that BAL-QE achieves 97% of the SOTA performance in WMT19 En-De and En-Ru QE tasks by only training 3% of parameters within 4 hours on 4 Titan XP GPUs. Compared with the commonly used NuQE baseline, BAL-QE achieves 47% (En-Ru) and 75% (En-De) of performance promotions.</abstract>
<identifier type="citekey">yang-etal-2020-efficient</identifier>
<location>
<url>https://aclanthology.org/2020.eamt-1.4</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>29</start>
<end>34</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficient Transfer Learning for Quality Estimation with Bottleneck Adapter Layer
%A Yang, Hao
%A Wang, Minghan
%A Xie, Ning
%A Qin, Ying
%A Deng, Yao
%Y Martins, André
%Y Moniz, Helena
%Y Fumega, Sara
%Y Martins, Bruno
%Y Batista, Fernando
%Y Coheur, Luisa
%Y Parra, Carla
%Y Trancoso, Isabel
%Y Turchi, Marco
%Y Bisazza, Arianna
%Y Moorkens, Joss
%Y Guerberof, Ana
%Y Nurminen, Mary
%Y Marg, Lena
%Y Forcada, Mikel L.
%S Proceedings of the 22nd Annual Conference of the European Association for Machine Translation
%D 2020
%8 November
%I European Association for Machine Translation
%C Lisboa, Portugal
%F yang-etal-2020-efficient
%X The Predictor-Estimator framework for quality estimation (QE) is commonly used for its strong performance. Where the predictor and estimator works on feature extraction and quality evaluation, respectively. However, training the predictor from scratch is computationally expensive. In this paper, we propose an efficient transfer learning framework to transfer knowledge from NMT dataset into QE models. A Predictor-Estimator alike model named BAL-QE is also proposed, aiming to extract high quality features with pre-trained NMT model, and make classification with a fine-tuned Bottleneck Adapter Layer (BAL). The experiment shows that BAL-QE achieves 97% of the SOTA performance in WMT19 En-De and En-Ru QE tasks by only training 3% of parameters within 4 hours on 4 Titan XP GPUs. Compared with the commonly used NuQE baseline, BAL-QE achieves 47% (En-Ru) and 75% (En-De) of performance promotions.
%U https://aclanthology.org/2020.eamt-1.4
%P 29-34
Markdown (Informal)
[Efficient Transfer Learning for Quality Estimation with Bottleneck Adapter Layer](https://aclanthology.org/2020.eamt-1.4) (Yang et al., EAMT 2020)
ACL