Dual Embedding Space Model (DESM)
The Dual Embedding Space Model (DESM) is an information retrieval model that uses two word embeddings, one for query words and one for document words. It takes into account the vector similarity between each query…
Smart Vehicle Spaces
Vision and Language
Automatically describing visual content with natural language is a fundamental challenge of computer vision and multimedia. Sequence learning (e.g., Recurrent Neural Networks), attention mechanism, memory networks, etc., have attracted increasing attention on visual interpretation. In this project,…
The Fourth Dialog State Tracking Challenge
Social Computing Symposium 2016: Post Screen Personas and Listening Machines, Can machine learning be fair?
I’ll talk about how we need to rethink what we mean by an “algorithm” in the context of machine learning, and the implications for whether (and how) we can trust the opaque algorithms that make…