pith. sign in

arxiv: cmp-lg/9411009 · v1 · submitted 1994-11-03 · cmp-lg · cs.CL

Bootstrapping A Wide-Coverage CCG from FB-LTAG

classification cmp-lg cs.CL
keywords grammarwide-coveragextagnumbersimilaritiesadaptingadditionallows
0
0 comments X
read the original abstract

A number of researchers have noted the similarities between LTAGs and CCGs. Observing this resemblance, we felt that we could make use of the wide-coverage grammar developed in the XTAG project to build a wide-coverage CCG. To our knowledge there have been no attempts to construct a large-scale CCG parser with the lexicon to support it. In this paper, we describe such a system, built by adapting various XTAG components to CCG. We find that, despite the similarities between the formalisms, certain parts of the grammatical workload are distributed differently. In addition, the flexibility of CCG derivations allows the translated grammar to handle a number of ``non-constituent'' constructions which the XTAG grammar cannot.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.