Building A Recurrent Neural Network For Contextual Language Responses (IMAGE)

University of Texas at Austin, Texas Advanced Computing Center

Building A Recurrent Neural Network For Contextual Language Responses

Caption

Contextual language encoding model with narrative stimuli. Each word in the story is first projected into a 985-dimensional embedding space. Sequences of word representations are then fed into an LSTM network that was pre-trained as a language model.

Credit

Huth lab, UT Austin

Usage Restrictions

None

License

Licensed content

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.