CLIP
Title: Bridging NLP and brain science to improve natural language understanding
Abstract: Natural language processing systems have made impressive strides in producing useful task-oriented language tools - but even the most sophisticated NLP systems fall dramatically short of the human brain in robustness and nuance of language understanding. A particular area of need in NLP is that of sentence composition: the combinatory capacity that allows humans to generate and understand the meanings of infinite sentences based on their parts.
Title: On the syntactic abilities of recurrent neural networks
Title: Text, Entities, and Relevant Context for Complex Answer Retrieval
Title: The Theoretical Perspectives on Interactive Information Retrieval
Abstract: In this talk, Kevin will briefly introduce his past works with Information Foraging and Search Economic Theories to explain web search behavior and then offering a perspective on how the theory from Behavioural Economics can augment our understanding of web search behavior in Interactive Information Retrieval.
Title: Duolingo: Improving Language Learning and Assessment with Data
Title: Separate the Sheep from the Goats: On recognizing the Literal and Figurative Usages of Idioms
Title: Classification and clustering based on LDA-like models
Abstract: I introduce two studies used statistical model with latent variables similar to Latent Dirichllet Allocation (LDA) model.
Title: Language and Policy: Bringing Language Science & Analytics into Public Policy