An analogical parser for restricted domains
Donald Hindle · 1992
This note describes the current development of an approach to parsing designed to overcome some of the problems of existing parsers, particularly with respect to their utility as language models. The parser combines lexical and grammatical constraints into a uniform grammatical representation, is readily trainable (since the parser output is indistinguishable from the grammar input), and uses analogy to guess about the likelihood of constructions outside the grammar.