Conditional random fields: Probabilistic models for segmenting and labeling sequence data

Conditional random fields: Probabilistic models for segmenting and labeling sequence data (2001)

by John Lafferty

Citations:

Datum	Value	Source
TITLE	Conditional random fields: Probabilistic models for segmenting and labeling sequence data	INFERENCE
AUTHOR NAME	John Lafferty	SVM HeaderParse 0.2
AUTHOR AFFIL	; ∗WhizBang; † School of Computer Science, Carnegie Mellon University, Pittsburgh; ‡ Department of Computer and Information Science, University of Pennsylvania, Philadelphia	SVM HeaderParse 0.2
AUTHOR ADDR	; Labs–Research, 4616 Henry Street, Pittsburgh, PA 15213 USA; PA 15213 USA; PA 19104 USA	SVM HeaderParse 0.2
ABSTRACT	We present conditional random fields, 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.	SVM HeaderParse 0.2
YEAR	2001	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	282--289	INFERENCE
CITATIONS	25 found	ParsCit 1.0