Recursive Deep Learning for Modelling Compositional and Grounded Meaning Richard Socher, Metamind

Recursive Deep Learning for Modeling Compositional and Grounded Meaning In this talk, I will describe deep learning algorithms that learn representations for language that are useful for solving a variety of complex language tasks. I will focus on 3 projects: 1) Contextual sentiment analysis having an algorithm that actually learns what s positive in this sentence: The Android phone is better than the iPhone ); 2) Question answering to win trivia competitions (like IBM Watson s Jeopardy system but w