Semi-Markov Conditional Random Fields for Information Extraction

We describe semi-Markov conditional random fields (semi-CRFs), a conditionally trained version of semi-Markov chains. Intuitively, a semiCRF on an input sequence x outputs a "segmentation" of x, in which labels are assigned to segments (i.e., subsequences) of x rather than to individual elements xi of x. Importantly, features for semi-CRFs can measure properties of segments, and transitions within a segment can be non-Markovian. In spite of this additional power, exact learning and inference algorithms for semi-CRFs are polynomial-time--often only a small constant factor slower than conventional CRFs. In experiments on five named entity recognition problems, semi-CRFs generally outperform conventional CRFs.

• Type: Conference
• Year: 2004
• Where: NIPS
• Authors: Sunita Sarawagi, William W. Cohen
• Keywords: Conditional Random Fields, Conventional Crfs, Individual Elements Xi, NIPS 2004, NIPS 2007