Fine-Tuned Machine Translation Metrics Struggle in Unseen Domains

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zouhar, Vilém, Ding, Shuoyang, Currey, Anna, Badeka, Tatyana, Wang, Jenyuan, Thompson, Brian
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911901470949376
author Zouhar, Vilém
Ding, Shuoyang
Currey, Anna
Badeka, Tatyana
Wang, Jenyuan
Thompson, Brian
author_facet Zouhar, Vilém
Ding, Shuoyang
Currey, Anna
Badeka, Tatyana
Wang, Jenyuan
Thompson, Brian
contents We introduce a new, extensive multidimensional quality metrics (MQM) annotated dataset covering 11 language pairs in the biomedical domain. We use this dataset to investigate whether machine translation (MT) metrics which are fine-tuned on human-generated MT quality judgements are robust to domain shifts between training and inference. We find that fine-tuned metrics exhibit a substantial performance drop in the unseen domain scenario relative to metrics that rely on the surface form, as well as pre-trained metrics which are not fine-tuned on MT quality judgments.
format Preprint
id arxiv_https___arxiv_org_abs_2402_18747
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Fine-Tuned Machine Translation Metrics Struggle in Unseen Domains
Zouhar, Vilém
Ding, Shuoyang
Currey, Anna
Badeka, Tatyana
Wang, Jenyuan
Thompson, Brian
Computation and Language
Artificial Intelligence
We introduce a new, extensive multidimensional quality metrics (MQM) annotated dataset covering 11 language pairs in the biomedical domain. We use this dataset to investigate whether machine translation (MT) metrics which are fine-tuned on human-generated MT quality judgements are robust to domain shifts between training and inference. We find that fine-tuned metrics exhibit a substantial performance drop in the unseen domain scenario relative to metrics that rely on the surface form, as well as pre-trained metrics which are not fine-tuned on MT quality judgments.
title Fine-Tuned Machine Translation Metrics Struggle in Unseen Domains
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2402.18747