@inproceedings{kalimuthu-etal-2019-incremental,
title = "Incremental Domain Adaptation for Neural Machine Translation in Low-Resource Settings",
author = "Kalimuthu, Marimuthu and
Barz, Michael and
Sonntag, Daniel",
editor = "El-Hajj, Wassim and
Belguith, Lamia Hadrich and
Bougares, Fethi and
Magdy, Walid and
Zitouni, Imed and
Tomeh, Nadi and
El-Haj, Mahmoud and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Fourth Arabic Natural Language Processing Workshop",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-4601",
doi = "10.18653/v1/W19-4601",
pages = "1--10",
abstract = "We study the problem of incremental domain adaptation of a generic neural machine translation model with limited resources (e.g., budget and time) for human translations or model training. In this paper, we propose a novel query strategy for selecting {``}unlabeled{''} samples from a new domain based on sentence embeddings for Arabic. We accelerate the fine-tuning process of the generic model to the target domain. Specifically, our approach estimates the informativeness of instances from the target domain by comparing the distance of their sentence embeddings to embeddings from the generic domain. We perform machine translation experiments (Ar-to-En direction) for comparing a random sampling baseline with our new approach, similar to active learning, using two small update sets for simulating the work of human translators. For the prescribed setting we can save more than 50{\%} of the annotation costs without loss in quality, demonstrating the effectiveness of our approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kalimuthu-etal-2019-incremental">
<titleInfo>
<title>Incremental Domain Adaptation for Neural Machine Translation in Low-Resource Settings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marimuthu</namePart>
<namePart type="family">Kalimuthu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Barz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Sonntag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Arabic Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wassim</namePart>
<namePart type="family">El-Hajj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lamia</namePart>
<namePart type="given">Hadrich</namePart>
<namePart type="family">Belguith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We study the problem of incremental domain adaptation of a generic neural machine translation model with limited resources (e.g., budget and time) for human translations or model training. In this paper, we propose a novel query strategy for selecting “unlabeled” samples from a new domain based on sentence embeddings for Arabic. We accelerate the fine-tuning process of the generic model to the target domain. Specifically, our approach estimates the informativeness of instances from the target domain by comparing the distance of their sentence embeddings to embeddings from the generic domain. We perform machine translation experiments (Ar-to-En direction) for comparing a random sampling baseline with our new approach, similar to active learning, using two small update sets for simulating the work of human translators. For the prescribed setting we can save more than 50% of the annotation costs without loss in quality, demonstrating the effectiveness of our approach.</abstract>
<identifier type="citekey">kalimuthu-etal-2019-incremental</identifier>
<identifier type="doi">10.18653/v1/W19-4601</identifier>
<location>
<url>https://aclanthology.org/W19-4601</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>1</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Incremental Domain Adaptation for Neural Machine Translation in Low-Resource Settings
%A Kalimuthu, Marimuthu
%A Barz, Michael
%A Sonntag, Daniel
%Y El-Hajj, Wassim
%Y Belguith, Lamia Hadrich
%Y Bougares, Fethi
%Y Magdy, Walid
%Y Zitouni, Imed
%Y Tomeh, Nadi
%Y El-Haj, Mahmoud
%Y Zaghouani, Wajdi
%S Proceedings of the Fourth Arabic Natural Language Processing Workshop
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F kalimuthu-etal-2019-incremental
%X We study the problem of incremental domain adaptation of a generic neural machine translation model with limited resources (e.g., budget and time) for human translations or model training. In this paper, we propose a novel query strategy for selecting “unlabeled” samples from a new domain based on sentence embeddings for Arabic. We accelerate the fine-tuning process of the generic model to the target domain. Specifically, our approach estimates the informativeness of instances from the target domain by comparing the distance of their sentence embeddings to embeddings from the generic domain. We perform machine translation experiments (Ar-to-En direction) for comparing a random sampling baseline with our new approach, similar to active learning, using two small update sets for simulating the work of human translators. For the prescribed setting we can save more than 50% of the annotation costs without loss in quality, demonstrating the effectiveness of our approach.
%R 10.18653/v1/W19-4601
%U https://aclanthology.org/W19-4601
%U https://doi.org/10.18653/v1/W19-4601
%P 1-10
Markdown (Informal)
[Incremental Domain Adaptation for Neural Machine Translation in Low-Resource Settings](https://aclanthology.org/W19-4601) (Kalimuthu et al., WANLP 2019)
ACL