1. AUTASYS (AUtomatic Text Annotation SYStem) is a fully automatic and
menu-driven MS DOS program that
a: tokenises unrestricted English text input,
b: tags tokens with LOB, ICE, and SKELETON tagsets
c: and lemmatises tokens tagged with any of the three tagsets.
2. It has an estimated accuracy rate of c. 96% and is able to process over
20,000 tokens per minute on DIMENSION XPS P120c.
3. Descriptions of AUTASYS include
Fang, A.C. 1996. "AUTASYS: Grammatical Tagging and Cross-Tagset Mapping". In
Comparing English Worldwide: The International Corpus of English, ed. by
Sidney Greenbaum. Oxford: Oxford University Press. pp 110-124.
4. AUTASYS is developed by and commercially available from
Alex Chengyu Fang
Department of Phonetics and Linguistics
University College London
Gower Street
London WC1E 6BT
UK
5. A free copy of AUTASYS 3.0 (ICE version) is available from me to the 18
or so ICE member teams on request, the condition being that it is used for
the annotation of ICE corpora only.