@inproceedings{haque-etal-2020-terminology,
title = "Terminology-Aware Sentence Mining for {NMT} Domain Adaptation: {ADAPT}{'}s Submission to the Adap-{MT} 2020 {E}nglish-to-{H}indi {AI} Translation Shared Task",
author = "Haque, Rejwanul and
Moslem, Yasmin and
Way, Andy",
editor = "Sharma, Dipti Misra and
Ekbal, Asif and
Arora, Karunesh and
Naskar, Sudip Kumar and
Ganguly, Dipankar and
L, Sobha and
Mamidi, Radhika and
Arora, Sunita and
Mishra, Pruthwik and
Mujadia, Vandan",
booktitle = "Proceedings of the 17th International Conference on Natural Language Processing (ICON): Adap-MT 2020 Shared Task",
month = dec,
year = "2020",
address = "Patna, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2020.icon-adapmt.4",
pages = "17--23",
abstract = "This paper describes the ADAPT Centre{'}s submission to the Adap-MT 2020 AI Translation Shared Task for English-to-Hindi. The neural machine translation (NMT) systems that we built to translate AI domain texts are state-of-the-art Transformer models. In order to improve the translation quality of our NMT systems, we made use of both in-domain and out-of-domain data for training and employed different fine-tuning techniques for adapting our NMT systems to this task, e.g. mixed fine-tuning and on-the-fly self-training. For this, we mined parallel sentence pairs and monolingual sentences from large out-of-domain data, and the mining process was facilitated through automatic extraction of terminology from the in-domain data. This paper outlines the experiments we carried out for this task and reports the performance of our NMT systems on the evaluation test set.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="haque-etal-2020-terminology">
<titleInfo>
<title>Terminology-Aware Sentence Mining for NMT Domain Adaptation: ADAPT’s Submission to the Adap-MT 2020 English-to-Hindi AI Translation Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rejwanul</namePart>
<namePart type="family">Haque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasmin</namePart>
<namePart type="family">Moslem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andy</namePart>
<namePart type="family">Way</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 17th International Conference on Natural Language Processing (ICON): Adap-MT 2020 Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dipti</namePart>
<namePart type="given">Misra</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karunesh</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudip</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Naskar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipankar</namePart>
<namePart type="family">Ganguly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="family">L</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Radhika</namePart>
<namePart type="family">Mamidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunita</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pruthwik</namePart>
<namePart type="family">Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vandan</namePart>
<namePart type="family">Mujadia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">Patna, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the ADAPT Centre’s submission to the Adap-MT 2020 AI Translation Shared Task for English-to-Hindi. The neural machine translation (NMT) systems that we built to translate AI domain texts are state-of-the-art Transformer models. In order to improve the translation quality of our NMT systems, we made use of both in-domain and out-of-domain data for training and employed different fine-tuning techniques for adapting our NMT systems to this task, e.g. mixed fine-tuning and on-the-fly self-training. For this, we mined parallel sentence pairs and monolingual sentences from large out-of-domain data, and the mining process was facilitated through automatic extraction of terminology from the in-domain data. This paper outlines the experiments we carried out for this task and reports the performance of our NMT systems on the evaluation test set.</abstract>
<identifier type="citekey">haque-etal-2020-terminology</identifier>
<location>
<url>https://aclanthology.org/2020.icon-adapmt.4</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>17</start>
<end>23</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Terminology-Aware Sentence Mining for NMT Domain Adaptation: ADAPT’s Submission to the Adap-MT 2020 English-to-Hindi AI Translation Shared Task
%A Haque, Rejwanul
%A Moslem, Yasmin
%A Way, Andy
%Y Sharma, Dipti Misra
%Y Ekbal, Asif
%Y Arora, Karunesh
%Y Naskar, Sudip Kumar
%Y Ganguly, Dipankar
%Y L, Sobha
%Y Mamidi, Radhika
%Y Arora, Sunita
%Y Mishra, Pruthwik
%Y Mujadia, Vandan
%S Proceedings of the 17th International Conference on Natural Language Processing (ICON): Adap-MT 2020 Shared Task
%D 2020
%8 December
%I NLP Association of India (NLPAI)
%C Patna, India
%F haque-etal-2020-terminology
%X This paper describes the ADAPT Centre’s submission to the Adap-MT 2020 AI Translation Shared Task for English-to-Hindi. The neural machine translation (NMT) systems that we built to translate AI domain texts are state-of-the-art Transformer models. In order to improve the translation quality of our NMT systems, we made use of both in-domain and out-of-domain data for training and employed different fine-tuning techniques for adapting our NMT systems to this task, e.g. mixed fine-tuning and on-the-fly self-training. For this, we mined parallel sentence pairs and monolingual sentences from large out-of-domain data, and the mining process was facilitated through automatic extraction of terminology from the in-domain data. This paper outlines the experiments we carried out for this task and reports the performance of our NMT systems on the evaluation test set.
%U https://aclanthology.org/2020.icon-adapmt.4
%P 17-23
Markdown (Informal)
[Terminology-Aware Sentence Mining for NMT Domain Adaptation: ADAPT’s Submission to the Adap-MT 2020 English-to-Hindi AI Translation Shared Task](https://aclanthology.org/2020.icon-adapmt.4) (Haque et al., ICON 2020)
ACL