Hallucinating to better text translation : vimarsana.com

A machine learning model called VALHALLA uses a trained neural network to understand and digest a source sentence in one language, hallucinate an image of what that sentence describes, and translate into a target language. The work was led by researchers from MIT, IBM, and UC San Diego.

Related Keywords

Germany , California , United States , France , Spain , Romania , Spanish , French , Romanian , German , Yoon Kim , Rogerio Feris , Nuno Vasconcelos , Yi Li , Chun Fu Richard Chen , David Cox , Artificial Intelligence Laboratory , Watson Ai Lab , Ibm , University Of California At San Diego , National Science Foundation , Department Of Electrical Engineering , San Diego , Electrical Engineering , Computer Science , Pattern Recognition Conference , Professor Nuno Vasconcelos , Rameswar Panda , National Science , Mit Ibm Watson Ai Lab , Sail , Machine Learning Models , Neural Networks , Hallucinations , Translation Software , Natural Language Processing , Walhalla , Machine Translation , Under Resourced Languages , Joon Kim , Encoder Decoder Architecture , Round Truth Image , Black Box ,