Confidence Estimation using Hidden-state CRF Models with Word and Phone-level Features
University of Cambridge / Engineering Dept.: We are one of the world's oldest universities and leading academic centres, and a self-governed community of scholars.
Exploiting User Turn Segmentation in Polylogue
Along conversations we are exposed to various external factors that might have strong influence on our conversational act in a specific moment. In terms of the behavior how natural language is used, this is all the more true if we look at the phenomena of words re-usage in conversations.
Multi-modal interaction with distant objects using eye gaze and multi-touch input
Tabletop interaction with objects in and out of reach is a common real world as well as virtual task. Gaze can be used as additional input modality in order to support search, selection and manipulation of distant objects on digital tabletop.
Structurally informed methods for improved sentiment analysis
The task of sentiment analysis is to automatically identify the opinions people express in natural language about some topic (such as a product or a work of art). For instance, the sentence "auto white balance is better than of the other canon cameras I have and they already do very-well" from a product review expresses a positive opinion about a specific camera.
Wikipedia-Based Named Entity Identification
One of the central tasks of natural language understanding is to identify the real world entity that a given linguistic expression is referring to. Solving this problem has become more realistic with the advent of machine readable repositories such as Wikipedia which provide unique identifiers of a large number of real world entities.
Programs & Grants
100 years ago nobody would have imagined that it may make sense to talk to machines. Today, in the days of speech recognition and speech synthesis to be found in cars, computers, phones and many other devices this is already normal. But it doesn't stop there.