Tom Kocmi, et al.: Preliminary Ranking of WMT25 General Machine Translation Systems https://arxiv.org/abs/2508.14909 https://arxiv.org/pdf/2508.14909 https://arxiv.org/html/2508.14909
August 22, 2025 at 6:29 AM
Everybody can reply
📐Task 1: Segment-level quality score prediction
Predict a quality score for each source–target segment pair, using document-level context and either ESA or MQM annotations.
Description: www2.statmt.org/wmt25/mteval...
Submission platform: www.codabench.org/competitions...
Predict a quality score for each source–target segment pair, using document-level context and either ESA or MQM annotations.
Description: www2.statmt.org/wmt25/mteval...
Submission platform: www.codabench.org/competitions...
MT Evaluation Subtask 1: Segment-Level Quality Score Prediction
www2.statmt.org
July 25, 2025 at 4:59 PM
Everybody can reply
Introducing the 1st shared task in Creole language machine translation, at WMT '25. Please consider making a submission; lots of progress to be made in this area! Official bsky account coming soon
www2.statmt.org/wmt25/creole...
www2.statmt.org/wmt25/creole...
Creole Language Translation
www2.statmt.org
May 7, 2025 at 1:33 PM
Everybody can reply
1 likes
[2025-08-26] 📚 Updates in #AIMat
(1) Preliminary Ranking of WMT25 General Machine Translation Systems
🔍 More at researchtrend.ai/communities/AIMat
(1) Preliminary Ranking of WMT25 General Machine Translation Systems
🔍 More at researchtrend.ai/communities/AIMat
August 26, 2025 at 3:09 AM
Everybody can reply
Hossain Shaikh Saadi, Minh Duc Bui, Mario Sanz-Guerrero, Katharina von der Wense: JGU Mainz's Submission to the WMT25 Shared Task on LLMs with Limited Resources for Slavic Languages: MT and QA https://arxiv.org/abs/2509.22490 https://arxiv.org/pdf/2509.22490 https://arxiv.org/html/2509.22490
September 29, 2025 at 6:31 AM
Everybody can reply
Lei Pang, Hanyi Mao, Quanjia Xiao, HaiXiao Liu, Xiangyi Li: In2x at WMT25 Translation Task https://arxiv.org/abs/2508.14472 https://arxiv.org/pdf/2508.14472 https://arxiv.org/html/2508.14472
August 21, 2025 at 6:30 AM
Everybody can reply
1 reposts
📐Task 3: Quality-informed segment-level error correction
Automatically post-edit machine-translated text using quality annotations to generate minimal and accurate corrections.
Description: www2.statmt.org/wmt25/mteval...
Submission platform: www.codabench.org/competitions...
Automatically post-edit machine-translated text using quality annotations to generate minimal and accurate corrections.
Description: www2.statmt.org/wmt25/mteval...
Submission platform: www.codabench.org/competitions...
QE-informed Segment-level Error Correction
www2.statmt.org
July 25, 2025 at 4:59 PM
Everybody can reply
Tom Kocmi, Eleftherios Avramidis, Rachel Bawden, Ond\v{r}ej Bojar, Konstantin Dranch, Anton Dvorkovich, Sergey Dukanov, Natalia Fedorova, Mark Fishel, Markus Freitag, Thamme Gowda, ...
Preliminary Ranking of WMT25 General Machine Translation Systems
https://arxiv.org/abs/2508.14909
Preliminary Ranking of WMT25 General Machine Translation Systems
https://arxiv.org/abs/2508.14909
August 22, 2025 at 7:39 AM
Everybody can reply
Hossain Shaikh Saadi, Minh Duc Bui, Mario Sanz-Guerrero, Katharina von der Wense
JGU Mainz's Submission to the WMT25 Shared Task on LLMs with Limited Resources for Slavic Languages: MT and QA
https://arxiv.org/abs/2509.22490
JGU Mainz's Submission to the WMT25 Shared Task on LLMs with Limited Resources for Slavic Languages: MT and QA
https://arxiv.org/abs/2509.22490
September 29, 2025 at 6:02 AM
Everybody can reply
🎉 Terminology Shared Task @WMT25: Paper Out 🎉
Highlights:
- sentence translation seems solvable, document translation is still challenging
- better systems benefit more from proper terminologies
- term-based metrics correlate poorly with general translation quality
www2.statmt.org/wmt25/pdf/20...
Highlights:
- sentence translation seems solvable, document translation is still challenging
- better systems benefit more from proper terminologies
- term-based metrics correlate poorly with general translation quality
www2.statmt.org/wmt25/pdf/20...
www2.statmt.org
October 24, 2025 at 7:57 PM
Everybody can reply
1 reposts
1 likes
📐Task 2: Span-level error detection
Identify and locate translation errors within each segment (start/end indices) and classify their severity.
Description: www2.statmt.org/wmt25/mteval...
Submission platform: www.codabench.org/competitions...
Identify and locate translation errors within each segment (start/end indices) and classify their severity.
Description: www2.statmt.org/wmt25/mteval...
Submission platform: www.codabench.org/competitions...
Fine-grained error span detection
www2.statmt.org
July 25, 2025 at 4:59 PM
Everybody can reply
2. "Improved Norwegian Bokmål Translations for FLORES" by Petter Mæhlum, Anders Næss Evensen and Yves Scherrer
(in proceedings of the WMT 2025 workshop)
www2.statmt.org/wmt25/
(in proceedings of the WMT 2025 workshop)
www2.statmt.org/wmt25/
WMT 2025
www2.statmt.org
October 21, 2025 at 3:27 PM
Everybody can reply
What to do now?
- Download the dataset and benchmark multilingual models: huggingface.co/datasets/ope...
- Subscribe to our newsletter: openlanguagedata.substack.com/about
- Participate in the WMT25 Open Data shared task to enrich open datasets with new languages www2.statmt.org/wmt25/open-d...
- Download the dataset and benchmark multilingual models: huggingface.co/datasets/ope...
- Subscribe to our newsletter: openlanguagedata.substack.com/about
- Participate in the WMT25 Open Data shared task to enrich open datasets with new languages www2.statmt.org/wmt25/open-d...
July 5, 2025 at 1:15 PM
Everybody can reply
1 likes
One way to raise the bar is by rethinking the source selection process: instead of random samples, we built model that chooses the most difficult data for translation. And we’ve already put our work into practice: this year’s WMT25 General MT test set use our approach to make eval more challenging.
September 16, 2025 at 9:51 AM
Everybody can reply
2 likes
* Revamped constrained track – No restrictions on training data except licensing; all open models under 20B parameters are allowed.
* More challenging sources; long-context translation; prompt preambles; and much more.
📌 All details are available at www2.statmt.org/wmt25/transl...
* More challenging sources; long-context translation; prompt preambles; and much more.
📌 All details are available at www2.statmt.org/wmt25/transl...
Shared Task: General Machine Translation
www2.statmt.org
February 20, 2025 at 9:31 PM
Everybody can reply
2 likes
📣Take part in 3rd Terminology shared task @WMT!📣
This year:
👉5 language pairs: EN->{ES, RU, DE, ZH},
👉2 tracks - sentence-level and doc-level translation,
👉authentic data from 2 domains: finance and IT!
www2.statmt.org/wmt25/termin...
Don't miss an opportunity - we only do it once in two years😏
This year:
👉5 language pairs: EN->{ES, RU, DE, ZH},
👉2 tracks - sentence-level and doc-level translation,
👉authentic data from 2 domains: finance and IT!
www2.statmt.org/wmt25/termin...
Don't miss an opportunity - we only do it once in two years😏
Terminology Translation Task
www2.statmt.org
June 6, 2025 at 3:54 PM
Everybody can reply
2 reposts
2 quotes
3 likes
Organizers are happy to help with any questions. 🙂
Website with all details and contacts: www2.statmt.org/wmt25/mteval...
Website with all details and contacts: www2.statmt.org/wmt25/mteval...
Shared task: Automated Translation Quality Evaluation Systems
www2.statmt.org
July 25, 2025 at 4:59 PM
Everybody can reply
JGU Mainz fine‑tuned the 3‑billion‑parameter Qwen2.5‑3B‑Instruct model for translation and QA in Ukrainian, Upper Sorbian and Lower Sorbian, showing gains over the WMT25 baseline. Read more: https://getnews.me/jgu-mainz-advances-low-resource-slavic-translation-and-qa-with-qwen2-5-llm/ #qwen #slavic
September 29, 2025 at 3:45 PM
Everybody can reply
📢 Announcing the first Shared Task in Translation for Creole Languages, part of WMT'25 ‼️‼️
🌎🌍🌏 www2.statmt.org/wmt25/creole...
🌎🌍🌏 www2.statmt.org/wmt25/creole...
Creole Language Translation
www2.statmt.org
June 5, 2025 at 3:30 AM
Everybody can reply
1 likes
Whoa the #WMT25 results on MT Evaluation are wild! ChrF outperforms pretty much all neural metrics 🙀
October 18, 2025 at 5:17 AM
Everybody can reply
Javier Garcia Gilabert, et al.: From SALAMANDRA to SALAMANDRATA: BSC Submission for WMT25 General Machine Translation Shared Task https://arxiv.org/abs/2508.12774 https://arxiv.org/pdf/2508.12774 https://arxiv.org/html/2508.12774
August 19, 2025 at 6:30 AM
Everybody can reply
the paper www2.statmt.org/wmt25/pdf/20...
www2.statmt.org
October 18, 2025 at 5:17 AM
Everybody can reply
Lei Pang, Hanyi Mao, Quanjia Xiao, HaiXiao Liu, Xiangyi Li
In2x at WMT25 Translation Task
https://arxiv.org/abs/2508.14472
In2x at WMT25 Translation Task
https://arxiv.org/abs/2508.14472
August 21, 2025 at 5:33 AM
Everybody can reply
Big news from WMT! 🎉 We are expanding beyond MT and launching a new multilingual instruction shared task. Our goal is to foster truly multilingual LLM evaluation and best practices in automatic and human evaluation. Join us and build the winning multilingual system!
www2.statmt.org/wmt25/multil...
www2.statmt.org/wmt25/multil...
Multilingual Instruction Shared Task
www2.statmt.org
March 11, 2025 at 6:26 PM
Everybody can reply
7 reposts
2 quotes
12 likes