Abstract | ||
---|---|---|
XTAG is an ongoing project to develop a wide-coverage grammar for English,
based on the Feature-based Lexicalized Tree Adjoining Grammar (FB-LTAG)
formalism. The XTAG system integrates a morphological analyzer, an N-best
part-of-speech tagger, an Early-style parser and an X-window interface, along
with a wide-coverage grammar for English developed using the system. This
system serves as a linguist's workbench for developing FB-LTAG specifications.
This paper presents a description of and recent improvements to the various
components of the XTAG system. It also presents the recent performance of the
wide-coverage grammar on various corpora and compares it against the
performance of other wide-coverage and domain-specific grammars. |
Year | Venue | Keywords |
---|---|---|
1994 | arXiv: Computation and Language | part of speech,system integration |
Field | DocType | Volume |
Rule-based machine translation,Tree-adjoining grammar,Attribute grammar,Workbench,Programming language,Computer science,Operator-precedence grammar,Grammar,Artificial intelligence,Natural language processing,Parsing | Journal | abs/cmp-lg/9411006 |
ISSN | Citations | PageRank |
Proceedings of TAG+3, 1994 | 1 | 0.44 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Christy Doran | 1 | 85 | 11.93 |
Dania Egedi | 2 | 114 | 30.16 |
Beth Ann Hockey | 3 | 212 | 36.35 |
B. Srinivas | 4 | 152 | 17.90 |