Projects
Neural Machine Translation provides very useful representation for the language in context. The sentences and words representation leaned from Neural Machine translation models can be efficiently used to boost the performance of many Natural Language Understanding (NLU) tasks that usually…
Machine translation has become a crucial component for enabling global communication. Millions of people are using online translation systems and mobile applications to communicate across language barriers. Machine translation has made rapid advances in recent years with the deep learning…
Spoken language translation is usually limited by the non-availability of the parallel data. We generate synthetic data for Neural Machine Translation of Spoken-Dialects. We introduce a novel approach to generate synthetic data for training Neural Machine Translation systems. The proposed…
We are using Neural Machine Translation (NMT) to achieve state-of-the-art translation performance. We are working on large scale / real-time translation systems to support high quality translation for various languages. We used LSTM Sequence-to-Sequence models. Many of our systems achieved…
Established:
2015 December: Skype Translator includes Spanish, Portuguese, French, German, Italian and Chinese (Mandarin). Conversation translation added to the IOS and Android Microsoft Translator apps. October: Skype Translator begins rolling out to Skype desktop for all users. May: Microsoft opens the…
Established:
A Microsoft Research innovation, TrueText takes the literal text and transforms it to more closely reflect user intent. It achieves this by removing speech disfluencies, such as “um”s and “ah”s, as well as stutters and repetitions. The text is also…
Established:
Microsoft Translator Hub empowers businesses and communities to build, train, and deploy customized automatic language translation systems—bringing better and specialized translation quality to established languages, and first-time automatic translation capabilities to the many languages that are not yet supported by…