Abstract

We describe new algorithms for training tagging models, as an alternative to maximum-entropy models or conditional random fields (CRFs). The algorithms rely on Viterbi decoding of training examples, combined with simple additive updates. We describe theory justifying the algorithms through a modification of the proof of convergence of the perceptron algorithm for classification problems. We give experimental results on part-of-speech tagging and base noun phrase chunking, in both cases showing improvements over results for a maximum-entropy tagger.

Citations

1655	M: Building a Large Annotated Corpus of English: The Penn Tree Bank - Marcus, Santorini, et al. - 1993
1548	F: Conditional Random Fields: Probabilistic models for segmenting and labeling sequence data - Lafferty, McCallum, et al. - 2001
662	Transformation-based error driven learning and natural language processing: A case study in parts of speech tagging - Brill - 1995
355	Maximum entropy Markov models for information extraction and segmentation - McCallum, Freitag, et al. - 2000
337	Text chunking using transformation-based learning - Ramshaw, Marcus - 1995
311	Large margin classification using the perceptron algorithm - Freund, Schapire - 1999
274	A Maximum Entropy Part-Of-Speech Tagger - Ratnaparkhi - 1996
204	Convolution kernels for natural languages - Collins, Duffy - 2001
164	N: New Ranking Algorithms for Parsing and Tagging: Kernels over Discrete Structures, and the Voted Perceptron - Collins, Duffy
49	On weak learning - HELMBOLD, WARMUTH - 1995
13	Ranking algorithms for named entity extraction: Boosting and the voted perceptron - Collins - 2002
13	Conditional random Probabilistic models for segmenting and labeling sequence data - Laerty, McCallum, et al. - 2001
2	Large margin classication using the Perceptron algorithm - Freund, Schapire - 1999