Enriching the knowledge sources used in a maximum entropy part-of-speech tagger

Published 1 January 2000Open access

Kristina Toutanova, Christopher D. Manning

DOI10.3115/1117794.1117802

Source URL

Citations948

View PDF

TL;DR

Abstract

This paper presents results for a maximum-entropy-based part of speech tagger, which achieves superior performance principally by enriching the information sources used for tagging. In particular, we get improved results by incorporating these features: (i) more extensive treatment of capitalization for unknown words; (ii) features for the disambiguation of the tense forms of verbs; (iii) features for disambiguating particles from prepositions and adverbs. The best resulting accuracy for the tagger on the Penn Treebank is 96.86% overall, and 86.91% on previously unseen words.

Keywords

Computer Science

Foundations of statistical natural language processing

9,996 Citations1999Christopher D. Manning, Hinrich Schütze

Computational LinguisticsA maximum entropy approach to natural language processing

3,120 Citations1996Adam Berger, Vincent J. Della Pietra +1 more

A maximum-likelihood approach for automatically constructing maximum entropy models is presented and how to implement this approach efficiently is described, using as examples several problems in natural language processing.

Journal of the American Statistical AssociationStatistical Methods for Speech Recognition

1,988 Citations1999Don X. Sun, Frederick Jelinek

The speech recognition problem hidden Markov models the acoustic model basic language modelling the Viterbi search hypothesis search on a tree and the fast match elements of information theory.

A maximum-entropy-inspired parser

1,496 Citations2000Eugene Charniak

A new parser for parsing down to Penn tree-bank style parse trees that achieves 90.1% average precision/recall for sentences of length 40 and less and 89.5% when trained and tested on the previously established sections of the Wall Street Journal treebank is presented.

TnT

1,329 Citations2000Thorsten Brants

Contrary to claims found elsewhere in the literature, it is argued that a tagger based on Markov models performs at least as well as other current approaches, including the Maximum Entropy framework.

View PDF

Maximum Entropy Model for Part-Of-Speech Tagging

1,276 Citations1996Adwait Ratnaparkhi

A statistical model which trains from a corpus annotated with Part Of Speech tags and assigns them to previously unseen text with state of the art accuracy and discusses the corpus consistency problems discovered during the implementation of these features.

ScholarlyCommons (University of Pennsylvania)Maximum entropy models for natural language ambiguity resolution

432 Citations1998Adwait Ratnaparkhi, Mitchell P. Marcus

This thesis demonstrates that several important kinds of natural language ambiguities can be resolved to state-of-the-art accuracies using a single statistical modeling technique based on the principle of maximum entropy.

View PDF

arXiv (Cornell University)TnT - A Statistical Part-of-Speech Tagger

325 Citations2000Thorsten Brants

View PDF

Computational LinguisticsPeriods, Capitalized Words, etc.

93 Citations2002Andrei Mikheev

This approach proved to be robust to domain shifts and new lexica and produced performance on the level with the highest reported results when incorporated into a part-of-speech tagger and helped reduce the error rate significantly on capitalized words and sentence boundaries.

Comparing a linguistic and a stochastic tagger

68 Citations1997Christer Samuelsson, Atro Voutilainen

EngCG-2, a constraint-based morphological tagger, is compared in a double-blind test with a state-of-the-art statistical tagger on a common disambiguation task using a common tag set and the issues of priming effects compromising the results and disagreement between human annotators are addressed.