S3 (2011-2012)

Structured Sparsity for Structured Prediction

Linear models have enjoyed great success in structured prediction in NLP. While a lot of progress has been made on efficient training with several loss functions, the problem of endowing learners with a mechanism for feature selection is still unsolved. … Read More

SSS: Separation of Synchronous Sources

The problem of separating synchronous sources (SSS) is a case of blind source separation (BSS) where independence of the sources is not satisfied. In SSS, the sources are assumed to be complex-valued, and different sources are phase-locked, which means that … Read More

Development of the Bing search engine at the Microsoft Language Development Center

The Microsoft Language Development Center has been collaborating with the Munich Search Technology center to improve the query understanding module of the Bing search engine. In this talk we will start by providing an overview of the main components of … Read More