Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
John Lafferty, Andrew McCallum, Fernando C. N. Pereira · ScholarlyCommons (University of Pennsylvania) · 2001
We present, a framework for building probabilistic models to segment and label sequence data. Conditional random fields offer several advantages over hidden Markov models and stochastic grammars for such tasks, including the ability to relax strong independence assumptions made in those models. Conditional random fields also avoid a fundamental limitation of maximum entropy Markov models (MEMMs) and other discriminative Markov models based on directed graphical models, which can be biased towards states with few successor states. We present iterative parameter estimation algorithms for conditional random fields and compare the performance of the resulting models to HMMs and MEMMs on synthetic and natural-language data. 1.
Cited by 12,553 works. Open-access PDF
Authors
References
- A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting
- Foundations of statistical natural language processing
- A maximum entropy approach to natural language processing
- Biological sequence analysis probabilistic models of proteins and nucleic acids
- Generalized Iterative Scaling for Log-Linear Models
- A Maximum Entropy Model for Part-Of-Speech Tagging
- Inducing features of random fields
- Transformation-based error-driven learning and natural language processing: a case study in part-of-speech tagging
- Maximum Entropy Markov Models for Information Extraction and Segmentation
- Gradient-based learning applied to document recognition