Evaluating Capabilities of MT Systems in Translating Idiomatic Expressions Using a Specialized Dataset

Multiword expressions (MWEs) are generally problematic for machine-translation systems. In this paper, we (i) describe a set, available on CLARIN-IS, of appr. 1,000 idiomatic MWEs which have been translated into English; (ii) use the set as a template for a hidden evaluation set, to be used in a new leaderboard for Icelandic language technology, and (iii) evaluate -- using both automatic and manual approaches -- four MT systems' abilities to translate MWEs from Icelandic to English using both datasets. We find that traditional transformer-based MT systems evaluated commonly fail when translating idiomatic expressions, while LLMs do much better.

Authors

Institutions

Publication Details

Journal
Linköping electronic conference proceedings
Published
2025-08-25
DOI
https://doi.org/10.3384/ecp216.02
Primary Topic
Natural Language Processing Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Evaluating Capabilities of MT Systems in Translating Idiomatic Expressions Using a Specialized Dataset

Einar Freyr Sigurðsson, Steinþór Steingrímsson
Linköping electronic conference proceedings
Natural Language Processing Techniques
article

Evaluating Capabilities of MT Systems in Translating Idiomatic Expressions Using a Specialized Dataset

Einar Freyr Sigurðsson, Steinþór Steingrímsson
article en

Abstract

Multiword expressions (MWEs) are generally problematic for machine-translation systems. In this paper, we (i) describe a set, available on CLARIN-IS, of appr. 1,000 idiomatic MWEs which have been translated into English; (ii) use the set as a template for a hidden evaluation set, to be used in a new leaderboard for Icelandic language technology, and (iii) evaluate -- using both automatic and manual approaches -- four MT systems' abilities to translate MWEs from Icelandic to English using both datasets. We find that traditional transformer-based MT systems evaluated commonly fail when translating idiomatic expressions, while LLMs do much better.

Linköping electronic conference proceedingsVol. 216
Árni Magnússon Institute for Icelandic Studies (IS)
Openalex Percentile: Top 56%
Natural Language Processing Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.