I The User's View --;1 Orientation --;2 A Short History of Tagging --;3 The Use of Tagging --;4 Tagsets --;5 Standards for Tagsets --;6 Performance of Taggers --;7 Selection and Operation of Taggers --;II The Implementer's View --;8 Automatic Taggers: An Introduction --;9 Tokenization --;10 Lexicons for Tagging --;11 Standardization in the Lexicon --;12 Morphological Analysis --;13 Tagging Unknown Words --;14 Hand-Crafted Rules --;15 Corpus-Based Rules --;16 Hidden Markov Models --;17 Machine Learning Approaches --;Appendix A: Example tagsets --;A.1 The Brown Corpus tagset --;A.2 The Penn Treebanktagset --;A.3 The EngCG tagset --;References.
In both the linguistic and the language engineering community, the creation and use of annotated text collections (or annotated corpora) is currently a hot topic. Unfortunately, the annotation of text material, especially more interesting linguistic annotation, is as yet a difficult task and can entail a substan- tial amount of human involvement.