The State of the Art in AI Translation with Tom Kocmi and Alon Lavie
Tom Kocmi and Alon Lavie on the latest WMT25 results that challenge claims of human...
#WMT
Array
(
[post_type] => post
[posts_per_page] => 12
[paged] => 1
[post_status] => publish
[tax_query] => Array
(
[relation] => AND
[0] => Array
(
[taxonomy] => post_tag
[field] => term_id
[terms] => 37036
[operator] => IN
)
)
)
What This Key Benchmark Reveals About AI Translation Evaluation in 2025
The 2025 edition of a key translation evaluation benchmark reveals why some metrics struggle and...
This LLM Tops Key AI Translation Benchmark in 2025
The 2025 edition of a key AI translation benchmark made this year’s tests tougher than...
With MetricX-24 Google Presents Latest Machine Translation Evaluation Metric
Google presents MetricX-24, its latest machine translation evaluation metric, which demonstrates significant performance improvements over...
Separating Accuracy and Fluency Improves Machine Translation Evaluation, Study Finds
Researchers highlight accuracy and fluency significance in translation. Separating the two may enhance machine translation...
Here Are the Best-Performing Machine Translation Evaluation Metrics
New research reveals the best-performing machine translation evaluation metrics, identifies major challenges in metrics development,...
Google Research Brings ‘Massively Multilingual’ Machine Translation to 200+ Languages
How necessary is parallel data for improving machine translation quality for low-resource languages? Google researchers...
Facebook (You Know, Meta) CTO Hypes WMT 2021 Win as ‘Truly Groundbreaking’
To be fair, this is the first-ever multilingual model to win the international machine translation...
Here Are the Top 10 Most Influential Research Papers on Neural Machine Translation
The most-cited neural machine translation research papers show how NMT came to dominate the field...
Google Explores New Way to Improve Google Translate: Paraphrasing by Humans
Google study shows human-paraphrased reference translations and new evaluation metric, BLEUP, produce better translations. Findings...
Yes, Now They Claim Machines ‘Outperform’ Human Translation in Adequacy
A group of AI researchers takes the perennial human vs. machine debate to the next...