Microsoft Says Large Language Models Are SotA Evaluators of Translation Quality
Microsoft introduces a GPT-based metric to evaluate translation quality and highlights the state-of-the-art capabilities of large language models (LLMs) in this task.
Microsoft introduces a GPT-based metric to evaluate translation quality and highlights the state-of-the-art capabilities of large language models (LLMs) in this task.
60-page report on interaction between human experts and AI in translation production; includes AI-enabled workflows, adoption rates, postediting, pricing models.
What you need to know about machine translation quality estimation (MTQE) — from benefits and challenges to industry adoption — as discussed by Adam Bittlingmayer and Conchita Laguardia.
Stunning majority of poll respondents think regulators should require flagging of machine translations. Plus your take on fully-automated translation quality reviews, etc.
Unbabel CEO Vasco Pedro joins SlatorPod to talk about machine translation for multilingual customer service, hiring top AI talent, the Lisbon startup scene, and learning from investors.
Memsource CEO David Čaněk talks about the recent acquisition and integration of Phrase and the future of AI and MT technology in shaping the localization industry.
New research suggests biases of QE datasets lead to guesstimates on machine translation quality. Researchers propose modified dataset, debut it at WMT 2020.
Amazon Prime Video researchers have developed a new quality estimation system for subtitle translations, which tells you when post-editing or rewrites are needed.
From technology, markets, and M&A to investment and the competitive landscape, the language industry leaders we interviewed in 2019 commented on a wide range of issues. Here are our top picks.
Characterizing post-editors based on their keystrokes, mouse activity, and other editing actions can help predict speed and, eventually, quality, says a new paper by Unbabel researchers.
As AI is booming, the world’s largest natural language processing conference doubled in size this year and attracted 2,500 researchers. Global tech companies came looking for fresh talent. And research teams from across the globe battled it out on shared machine translation tasks.
Memsource has released a second AI-powered feature, Machine Translation Quality
Google team publishes a detailed paper on its rapid progress in neural machine translation. Says new model running on Google’s Tensor Flow surpasses all other systems and approaches human translation.
Slator Weekly: Join over 15,500 subscribers and get the latest language industry intelligence every Friday
Tool Box: Join over 9,000 subscribers for your monthly linguist technology update.
Your information will not be shared with third parties. No Spam.
This will close in 0 seconds