This paper proposes a framework for semi-supervised structured output learning (SOL), specifically for sequence labeling, based on a hybrid generative and discriminative approach...
Problems stemming from domain adaptation continue to plague the statistical natural language processing community. There has been continuing work trying to find general purpose al...
Conditional random fields (CRFs) have been quite successful in various machine learning tasks. However, as larger and larger data become acceptable for the current computational ma...
We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including: part-of-speech tagging, chunki...
Identity federation is a powerful scheme that links accounts of users maintained distinctly by different business partners. The concept of network identity is a driver for accele...