@inproceedings{dimakis-anastasopoulos-2026-style,
title = "Style-Aware Translation for Multi-Word Expressions in Low-Resource Languages",
author = "Dimakis, Antonios and
Anastasopoulos, Antonios",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.127/",
pages = "2482--2513",
ISBN = "979-8-89176-444-6",
abstract = "While neural machine translation (NMT) has achieved remarkable parity with human performance in general domains, handling multi-word expressions (MWEs) remains a persistent challenge, particularly in low-resource settings. This difficulty is twofold: models need not only decode the non-compositional meaning of MWEs but also navigate the stylistic choice between idiomatic ({''}MWE'') and literal ({''}plain'') outputs. In this study, we introduce a new 4-way parallel dataset for Greek and English, comprising of Greek and English MWE and plain sentences. We evaluate the style-transfer and style-switching capabilities of state-of-the-art Large Language Models (LLMs) across four tasks. Using traditional metrics, we demonstrate that LLMs often struggle with style-aware translation. Furthermore, we introduce StyleCOMET, a fine-tuned quality estimation metric to better evaluate stylistic nuances. Our results suggest that current limitations in MWE translation are a product of both model inability and metric-level insensitivity to idiomaticity."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dimakis-anastasopoulos-2026-style">
<titleInfo>
<title>Style-Aware Translation for Multi-Word Expressions in Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Dimakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>While neural machine translation (NMT) has achieved remarkable parity with human performance in general domains, handling multi-word expressions (MWEs) remains a persistent challenge, particularly in low-resource settings. This difficulty is twofold: models need not only decode the non-compositional meaning of MWEs but also navigate the stylistic choice between idiomatic (”MWE”) and literal (”plain”) outputs. In this study, we introduce a new 4-way parallel dataset for Greek and English, comprising of Greek and English MWE and plain sentences. We evaluate the style-transfer and style-switching capabilities of state-of-the-art Large Language Models (LLMs) across four tasks. Using traditional metrics, we demonstrate that LLMs often struggle with style-aware translation. Furthermore, we introduce StyleCOMET, a fine-tuned quality estimation metric to better evaluate stylistic nuances. Our results suggest that current limitations in MWE translation are a product of both model inability and metric-level insensitivity to idiomaticity.</abstract>
<identifier type="citekey">dimakis-anastasopoulos-2026-style</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.127/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>2482</start>
<end>2513</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Style-Aware Translation for Multi-Word Expressions in Low-Resource Languages
%A Dimakis, Antonios
%A Anastasopoulos, Antonios
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F dimakis-anastasopoulos-2026-style
%X While neural machine translation (NMT) has achieved remarkable parity with human performance in general domains, handling multi-word expressions (MWEs) remains a persistent challenge, particularly in low-resource settings. This difficulty is twofold: models need not only decode the non-compositional meaning of MWEs but also navigate the stylistic choice between idiomatic (”MWE”) and literal (”plain”) outputs. In this study, we introduce a new 4-way parallel dataset for Greek and English, comprising of Greek and English MWE and plain sentences. We evaluate the style-transfer and style-switching capabilities of state-of-the-art Large Language Models (LLMs) across four tasks. Using traditional metrics, we demonstrate that LLMs often struggle with style-aware translation. Furthermore, we introduce StyleCOMET, a fine-tuned quality estimation metric to better evaluate stylistic nuances. Our results suggest that current limitations in MWE translation are a product of both model inability and metric-level insensitivity to idiomaticity.
%U https://aclanthology.org/2026.findings-aacl.127/
%P 2482-2513
Markdown (Informal)
[Style-Aware Translation for Multi-Word Expressions in Low-Resource Languages](https://aclanthology.org/2026.findings-aacl.127/) (Dimakis & Anastasopoulos, Findings 2026)
ACL