A reader asked me on Linkedin if Universal translator was based on Google translate. I investigated, but I didn't get any good information so I made a comparison by machine translating the same content with Universal translator and then with Google translate. the first article, first clause of the European Constitution – Establishment of the Union… Continue reading Universal translator vs Google translate
I took three portions of three different French texts to be machine translated with Universal Translator into English. These are the three samples: first article, first clause of the European Constitution – Establishment of the Union (here the full version); the first part of an article from the French newspaper l'Express, click here to read the full text;… Continue reading Universal translator – App test
Automatic evaluation One method is the bleu score: bilingual evaluation understudy. Here MT output is compared to human translation: the higher the similarity between MT and the human version is, the higher the translation quality is considered. However, automatic evaluation ignores the difference among various styles and terminological choices. Manual evaluation Done by asking humans… Continue reading MT quality – Automatic metrics or manual evaluation?