Some Advances in Transformation-Based Part of Speech Tagging

Abstract

Most recent research in trainable part of speech taggers has explored stochastic tagging. While these taggers obtain high accuracy, linguistic information is captured indirectly, typically in tens of thousands of lexical and contextual probabilities. In [Brill92], a trainable rule-based tagger was described that obtained performance comparable to that of stochastic taggers, but captured relevant linguistic information in a small number of simple non-stochastic rules. In this paper, we describe a number of extensions to this rule-based tagger. First, we describe a method for expressing lexical relations in tagging that are not captured by stochastic taggers. Next, we show a rule-based approach to tagging unknown words. Finally, we show how the tagger can be extended into a k-best tagger, where multiple tags can be assigned to words in some cases of uncertainty.

6 Pages. Code available

Cited by in corpus (5)

• Apportioning Development Effort in a Probabilistic LR Parsing System through Evaluation
• Prospects for in-depth story understanding by computer
• New Methods, Current Trends and Software Infrastructure for NLP
• Heuristics and Parse Ranking
• TAKTAG: Two-phase learning method for hybrid statistical/rule-based part-of-speech disambiguation