@inproceedings{doi-etal-2026-simul,
title = "Simul-{COMET}: A Quality Metric for Simultaneous Interpretation in Distant Language Pair Considering Word Order Difference",
author = "Doi, Kosuke and
Makinae, Mana and
Sakai, Yusuke and
Kamigaito, Hidetaka and
Watanabe, Taro",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.2110/",
pages = "42515--42533",
ISBN = "979-8-89176-395-1",
abstract = "In simultaneous interpretation (SI), interpreters perform real-time translation by segmenting the source speech into chunks and translating them in the order they appear.Since surface-matching metrics such as BLEU correlate poorly with human evaluations, translation quality is often evaluated using neural metrics that measure semantic similarity, such as COMET.However, while SI translation ideally exhibits high monotonicity, COMET tends to assign higher scores to offline translations with long-distance reordering, because it is trained on such offline translation data.To address this gap, we propose Simul-COMET, a variation of COMET adapted for SI evaluation specifically designed for monotonicity.We train Simul-COMET on the SI-style translation data, which was converted from the offline translation of the COMET training data by leveraging large language models.In English{--}Japanese translation experiments, we demonstrate that Simul-COMET assigns higher scores to SI-style translations than to offline ones.Moreover, Simul-COMET shows stronger alignment with evaluation scores provided by professional interpreters than the original COMET.Simul-COMET is available at https://github.com/kosuked/simul-comet."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="doi-etal-2026-simul">
<titleInfo>
<title>Simul-COMET: A Quality Metric for Simultaneous Interpretation in Distant Language Pair Considering Word Order Difference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kosuke</namePart>
<namePart type="family">Doi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mana</namePart>
<namePart type="family">Makinae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Sakai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hidetaka</namePart>
<namePart type="family">Kamigaito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>In simultaneous interpretation (SI), interpreters perform real-time translation by segmenting the source speech into chunks and translating them in the order they appear.Since surface-matching metrics such as BLEU correlate poorly with human evaluations, translation quality is often evaluated using neural metrics that measure semantic similarity, such as COMET.However, while SI translation ideally exhibits high monotonicity, COMET tends to assign higher scores to offline translations with long-distance reordering, because it is trained on such offline translation data.To address this gap, we propose Simul-COMET, a variation of COMET adapted for SI evaluation specifically designed for monotonicity.We train Simul-COMET on the SI-style translation data, which was converted from the offline translation of the COMET training data by leveraging large language models.In English–Japanese translation experiments, we demonstrate that Simul-COMET assigns higher scores to SI-style translations than to offline ones.Moreover, Simul-COMET shows stronger alignment with evaluation scores provided by professional interpreters than the original COMET.Simul-COMET is available at https://github.com/kosuked/simul-comet.</abstract>
<identifier type="citekey">doi-etal-2026-simul</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.2110/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>42515</start>
<end>42533</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simul-COMET: A Quality Metric for Simultaneous Interpretation in Distant Language Pair Considering Word Order Difference
%A Doi, Kosuke
%A Makinae, Mana
%A Sakai, Yusuke
%A Kamigaito, Hidetaka
%A Watanabe, Taro
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F doi-etal-2026-simul
%X In simultaneous interpretation (SI), interpreters perform real-time translation by segmenting the source speech into chunks and translating them in the order they appear.Since surface-matching metrics such as BLEU correlate poorly with human evaluations, translation quality is often evaluated using neural metrics that measure semantic similarity, such as COMET.However, while SI translation ideally exhibits high monotonicity, COMET tends to assign higher scores to offline translations with long-distance reordering, because it is trained on such offline translation data.To address this gap, we propose Simul-COMET, a variation of COMET adapted for SI evaluation specifically designed for monotonicity.We train Simul-COMET on the SI-style translation data, which was converted from the offline translation of the COMET training data by leveraging large language models.In English–Japanese translation experiments, we demonstrate that Simul-COMET assigns higher scores to SI-style translations than to offline ones.Moreover, Simul-COMET shows stronger alignment with evaluation scores provided by professional interpreters than the original COMET.Simul-COMET is available at https://github.com/kosuked/simul-comet.
%U https://aclanthology.org/2026.findings-acl.2110/
%P 42515-42533
Markdown (Informal)
[Simul-COMET: A Quality Metric for Simultaneous Interpretation in Distant Language Pair Considering Word Order Difference](https://aclanthology.org/2026.findings-acl.2110/) (Doi et al., Findings 2026)
ACL