@inproceedings{baek-etal-2023-towards,
title = "Towards Accurate Translation via Semantically Appropriate Application of Lexical Constraints",
author = "Baek, Yujin and
Lee, Koanho and
Ki, Dayeon and
Park, Cheonbok and
Lee, Hyoung-Gyu and
Choo, Jaegul",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.298",
doi = "10.18653/v1/2023.findings-acl.298",
pages = "4839--4855",
abstract = "Lexically-constrained NMT (LNMT) aims to incorporate user-provided terminology into translations. Despite its practical advantages, existing work has not evaluated LNMT models under challenging real-world conditions. In this paper, we focus on two important but understudied issues that lie in the current evaluation process of LNMT studies. The model needs to cope with challenging lexical constraints that are {``}homographs{''} or {``}unseen{''} during training. To this end, we first design a homograph disambiguation module to differentiate the meanings of homographs. Moreover, we propose PLUMCOT which integrates contextually rich information about unseen lexical constraints from pre-trained language models and strengthens a copy mechanism of the pointer network via direct supervision of a copying score. We also release HOLLY, an evaluation benchmark for assessing the ability of model to cope with {``}homographic{''} and {``}unseen{''} lexical constraints. Experiments on HOLLY and the previous test setup show the effectiveness of our method. The effects of PLUMCOT are shown to be remarkable in {``}unseen{''} constraints. Our dataset is available at \url{https://github.com/papago-lab/HOLLY-benchmark}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="baek-etal-2023-towards">
<titleInfo>
<title>Towards Accurate Translation via Semantically Appropriate Application of Lexical Constraints</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yujin</namePart>
<namePart type="family">Baek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koanho</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dayeon</namePart>
<namePart type="family">Ki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheonbok</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyoung-Gyu</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaegul</namePart>
<namePart type="family">Choo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Lexically-constrained NMT (LNMT) aims to incorporate user-provided terminology into translations. Despite its practical advantages, existing work has not evaluated LNMT models under challenging real-world conditions. In this paper, we focus on two important but understudied issues that lie in the current evaluation process of LNMT studies. The model needs to cope with challenging lexical constraints that are “homographs” or “unseen” during training. To this end, we first design a homograph disambiguation module to differentiate the meanings of homographs. Moreover, we propose PLUMCOT which integrates contextually rich information about unseen lexical constraints from pre-trained language models and strengthens a copy mechanism of the pointer network via direct supervision of a copying score. We also release HOLLY, an evaluation benchmark for assessing the ability of model to cope with “homographic” and “unseen” lexical constraints. Experiments on HOLLY and the previous test setup show the effectiveness of our method. The effects of PLUMCOT are shown to be remarkable in “unseen” constraints. Our dataset is available at https://github.com/papago-lab/HOLLY-benchmark.</abstract>
<identifier type="citekey">baek-etal-2023-towards</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.298</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.298</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>4839</start>
<end>4855</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Accurate Translation via Semantically Appropriate Application of Lexical Constraints
%A Baek, Yujin
%A Lee, Koanho
%A Ki, Dayeon
%A Park, Cheonbok
%A Lee, Hyoung-Gyu
%A Choo, Jaegul
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F baek-etal-2023-towards
%X Lexically-constrained NMT (LNMT) aims to incorporate user-provided terminology into translations. Despite its practical advantages, existing work has not evaluated LNMT models under challenging real-world conditions. In this paper, we focus on two important but understudied issues that lie in the current evaluation process of LNMT studies. The model needs to cope with challenging lexical constraints that are “homographs” or “unseen” during training. To this end, we first design a homograph disambiguation module to differentiate the meanings of homographs. Moreover, we propose PLUMCOT which integrates contextually rich information about unseen lexical constraints from pre-trained language models and strengthens a copy mechanism of the pointer network via direct supervision of a copying score. We also release HOLLY, an evaluation benchmark for assessing the ability of model to cope with “homographic” and “unseen” lexical constraints. Experiments on HOLLY and the previous test setup show the effectiveness of our method. The effects of PLUMCOT are shown to be remarkable in “unseen” constraints. Our dataset is available at https://github.com/papago-lab/HOLLY-benchmark.
%R 10.18653/v1/2023.findings-acl.298
%U https://aclanthology.org/2023.findings-acl.298
%U https://doi.org/10.18653/v1/2023.findings-acl.298
%P 4839-4855
Markdown (Informal)
[Towards Accurate Translation via Semantically Appropriate Application of Lexical Constraints](https://aclanthology.org/2023.findings-acl.298) (Baek et al., Findings 2023)
ACL