Category Archives: Neural Machine Translation

Steve Dept, Founding Partner, and Devasmita Ghosh, Business Development Lead at cApStAn Linguistic Quality Control, are just back from Boston, USA, where they attended the Society for Industrial and Organizational Psychology (SIOP) conference 2023. This was an intense event packed with thought-provoking content. We see a shift from elation about the promises of AI and Large Language Models towards …

“cApStAn team just back from the Society for Industrial and Organizational Psychology (SIOP) conference 2023 in Boston”

The translator of the future is a human-machine hybrid The gist of a recent article in The Economist is precisely what we at cApStAn Linguistic Quality Control have been applying for years by looking at “augmented translator models” and man-machine interaction in translation environments. We believe that finding the right combination of automation and human intervention is the way forward. …

“The translator of the future is a human-machine hybrid”

In the 21st century, “accessibility” often includes language, but translating a test into the strongest language of all test takers may not be realistic. Nevertheless, passing or failing a test should not depend on reading proficiency. Tests and exams are a gate for life chances and—unless being proficient in the language of the test is …

“How fair is it to deliver your exams only in English?”

It is true that (much) more than half a century of research into machine translation (MT) has not resulted in a technical solution that comes close to “human parity”, contrary to claims based on obsolete metrics such as BLEU scores. It is also true that we have witnessed significant progress in the quality of raw …

“Why TAUS’ 3-step recipe for better machine translation does not work for all”

Imperfections in machine translation (MT) have long motivated systems for improving translations post-hoc with automatic post-editing (APE). (1) In contrast, up to now, little attention had been devoted to the problem of automatically correcting human-generated translations. A study introducing for the first time ever an automatic human translation correction model (TEC) was presented by language …

“After automated post-editing, APE, the next new hot topic is automated (human) translation error correction, or TEC”

by Pisana Ferrari – cApStAn Ambassador to the Global Village The book “Dancing on ropes. Translators at the balance of history”, written by Anna Aslanyan, is based on the author’s experience as a Russian-English translator and service interpreter. Aslanyan grew up in Moscow and lives in London. She writes for a number of publications, including …

““Dancing on Ropes. Translators at the balance of history” by Anna Aslanyan: a review”

by Pisana Ferrari – cApStAn Ambassador to the Global Village Google Cloud has recently announced the general availability of Document Translation, a new feature of Translation API Advanced, that lets you translate documents in formats such as Docx, PPTx, XLSx, and PDF while preserving document formatting. This includes right-to-left language support for PDFs, preservation of …

“New Google Cloud service allows you to translate documents while preserving the formatting”

by Pisana Ferrari – cApStAn Ambassador to the Global Village A recent Google AI blog post on the topic of gender bias in machine translation reports an ambitious but sensible endeavour: the creation of a dataset based on translated Wikipedia biographies. The aim of this dataset is to analyze common gender errors in machine translation. …

“Google AI Introduces A Dataset for Studying Gender Bias in Machine Translation”