This paper explores the use of the homotopy method for training a semi-supervised Hidden Markov Model (HMM) used for sequence labeling. We provide a novel polynomial-time algorith...
Using unlabeled data to help supervised learning has become an increasingly attractive methodology and proven to be effective in many applications. This paper applies semi-supervi...
We present conditional random fields, a framework for building probabilistic models to segment and label sequence data. Conditional random fields offer several advantages over hid...
John D. Lafferty, Andrew McCallum, Fernando C. N. ...
Background: Existing hidden Markov model decoding algorithms do not focus on approximately identifying the sequence feature boundaries. Results: We give a set of algorithms to com...
We introduce a new perceptron-based discriminative learning algorithm for labeling structured data such as sequences, trees, and graphs. Since it is fully kernelized and uses poin...