Abstract and Credits
ENGCG, the Constraint Grammar Parser of English, performs
morphosyntactic
analysis (tagging) of running English text. The parser employs a
morphological ("part-of-speech") disambiguator that makes 93-97% of
all running-text words in Written Standard English unambiguous while
99.7% of all words retain the correct analysis. The corresponding
figures for the shallow syntactic parser are 75-85% and 97-98%. The
system is available from
Lingsoft, Inc. (contact
info@lingsoft.fi).
ENGCG was developed at the
Department of General
Linguistics (Research Unit for Computational
Linguistics) at the
University of Helsinki.
Authors of the English description:
- Atro
Voutilainen
- Preprocessor, ENGTWOL lexicon, disambiguation constraints for
morphological ambiguities.
- Juha Heikkilä
- ENGTWOL lexicon.
- Arto Anttila and
Timo
Järvinen
- Constraint Syntax.
The morphological analyser is the two-level program by
Kimmo
Koskenniemi and Lingsoft, Inc. The parser was written in C by
Pasi
Tapanainen (Research Unit for Computational
Linguistics). The parsing speed is 400 words/second (Sun SPARCstation
10/30).
Mikko Silvonen
converted this introduction from Atro Voutilainen's info file on
ENGCG.
[ ENGCG Intro | Sample
Analysis ]
webmaster@lingsoft.fi
Last modified: Mon Jan 22 11:22:03 1996