No Post-Editing Output: Microsoft Releases Massive Machine Translation Test Set
Microsoft’s NTREX-128, the second largest human-translated test set, is another benchmark for the evaluation of massively multilingual machine translation research.
Microsoft’s NTREX-128, the second largest human-translated test set, is another benchmark for the evaluation of massively multilingual machine translation research.
Amazon releases MT-GenEval, a realistic dataset for evaluating gender bias in machine translation, to better understand how MT models perform on gender translation accuracy.
Researchers revisit controlled language as a means of improving MT quality. A new methodology based on stylistic quality is said to eliminate repeated fine tuning.
Unlike some fields in machine learning, machine translation still requires large sets of training data. The solution? Creating more data when none (or not enough) exists.
At SlatorCon Remote December 2022, Bryan Murphy, CEO of Smartling, talks about leveraging AI and automation to drive growth and reduce costs in the event of a recession.
At SlatorCon Remote December 2022, Konstantin Savenkov, CEO at Intento, on machine translation bottlenecks, value drivers, ROI, and the future of the global language market.
All you need to know about how you score against postediting translation speed standards and the factors affecting your performance.
LSPs think of diversification, DeepL retains its edge after five years, cultural neutralization of source marketing language, automatic transcription far from general adoption.
Very fluent but not yet highly accurate — this is how Google researchers describe machine translation performance of large language models versus state-of-the-art MT.
BNP Paribas, Europe’s second largest bank, applies domain adaptation for multilingual neural machine translation models — without excessive loss of knowledge across language pairs.
A literary translation experiment using Google Translate and paragraph alignment reveals only slight improvements in post-edited text versus professional human translations.
Researchers from Amazon present a simple procedure for extending pretrained machine translation evaluation metrics to the document level.
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.
When researchers experimented with machine translation to simplify medical content for patients, the results were mixed but promising.
Machine dubbing startup, Dubdub, raises USD 1m in seed funding. Finds traction with marketing, creative agencies; sees “strong pull” from production houses, OTT.
An analysis of 300+ LinkedIn profiles associated with DeepL suggest the world's fastest-growing MT company has set its sights on enterprise localization and language services customers.
Computer researchers at the University of Maryland experiment with machine translation to show how global meetings can be optimized.
Natural language generation (NLG) startups can help content creators write copy in multiple languages. But are AI writers a threat or an opportunity for LSPs?
XL8 CEO, Tim Jung, on using machine translation and expert-in-the-loop AI technology for media localization and live events.
Swiss SaaS platform, Neur.on, designed for localization users, buyers in legal and finance sectors, announces USD 1.6m investment round.