How Large Language Models Improve Document-Level AI Translation
University of Zurich and Huawei researchers show how LLMs improve document-level AI translation by preserving...
Maria Stasimioti
Array
(
[post_type] => post
[posts_per_page] => 12
[paged] => 15
[post_status] => publish
[author] => 2795
)
Does Word-Level Quality Estimation Really Improve AI Translation Post-Editing?
A new study investigates the impact of word-level quality estimation on post-editing. While it may...
US Healthcare Firm Converts Multilingual Speech into Structured Medical Reports
Inspired Spine’s SURI converts multilingual doctor-patient conversations into structured medical reports using automatic speech recognition...
Multi-Agent AI Framework Aims to Improve Cultural Adaptation in AI Translation
Researchers from Shahjalal University of Science and Technology and the University of Oklahoma propose a...
How France’s Inria Aims to Improve AI Translation for Low-Resource Languages
Inria improves AI translation for low-resource languages by breaking sentences into simpler phrases, translating them...
Translationese Remains a Challenge for Large Language Models, Study Finds
A new study finds that translationese — unnatural, overly literal translations — remains a persistent...
Unbabel Tackles Metric Bias in AI Translation
Unbabel exposes how using the same metrics for both training and evaluation can create misleading...
Alibaba Says Large Reasoning Models Are Redefining AI Translation
Alibaba claims large reasoning models excel in stylized and document-level translation, but high computational costs...
How to Balance Cost and Quality in AI Translation Evaluation
Researchers show how to reduce computational overhead in LLM-based translation evaluation while maintaining accuracy, offering...
New Research Tackles Key Challenges in AI Speech Recognition and Translation
Tsinghua and Cambridge researchers introduce a technique that expands multilingual speech models without full retraining,...
New Research Explores How to Boost Large Language Models’ Multilingual Performance
Researchers present a new training method that improves large language model performance across languages, especially...