Social Media

First story detection, Opinion Retrieval, Predicting Retweets and Deletions, ...

Machine Translation

Randomised language models, streaming, non-parametric Bayesian approaches, large-scale discriminative approaches, evaluation, paraphrasing, system descriptions, misc.

Conditional Random Fields

Logarithmic opinion pools, scaling, gradient-based training regimes.

Active Learning

Reuse, relationship to ensemble methods.

Bootstrapping

Co-training for parsers

Other papers

Locality sensitive hashing, shallow parsing, grammar learning, reviews etc.