| Download | - View final version: MSLC25: metric performance on low-quality machine translation, empty strings, and language variants (PDF, 8.5 MiB)
|
|---|
| DOI | Resolve DOI: https://doi.org/10.18653/v1/2025.wmt-1.69 |
|---|
| Author | Search for: Knowles, Rebecca1ORCID identifier: https://orcid.org/0000-0002-1647-584X; Search for: Larkin, Samuel1ORCID identifier: https://orcid.org/0009-0000-6147-9631; Search for: Lo, Chi-Kiu1ORCID identifier: https://orcid.org/0000-0001-8714-7846 |
|---|
| Affiliation | - National Research Council Canada. Digital Technologies
|
|---|
| Format | Text, Article |
|---|
| Conference | Tenth Conference on Machine Translation, November 8-9, 2025, Suzhou, China |
|---|
| Abstract | In this challenge set, we examine how automatic metrics for machine translation perform on a wide variety of machine translation output, covering a wider range of quality than the WMT submissions. We also explore metric results on specific types of corner cases, such as empty strings, wrong- or mixed-language text, and more. We primarily focus on Japanese–Chinese data, with some work on English and Czech. |
|---|
| Publication date | 2025 |
|---|
| Publisher | Association for Computational Linguistics |
|---|
| Copyright statement | - ©2025 His
Majesty the King in Right of Canada, as represented by the National Research Council,
Canada
|
|---|
| Licence | |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | e30337a8-5f0c-4b66-813a-d9ba4f748f60 |
|---|
| Record created | 2026-02-16 |
|---|
| Record modified | 2026-03-18 |
|---|
