1996/04/19 by Robert John Freeman, Freeman, Robert John
Arts and Humanities · Computer Science · Psychology · #Natural Language Processing Techniques #Second Language Acquisition and Learning #Translation Studies and Practices #cmp-lg #cs.CL
paper · pdf · doi:10.48550/arxiv.cmp-lg/9604007
7 pages, uuencoded gzipped Postscript
arxiv created 1996/04/19 · arxiv updated 2009/11/30
A perspective of statistical language models which emphasizes their collocational aspect is advocated. It is suggested that strings be generalized in terms of classes of relationships instead of classes of objects. The single most important characteristic of such a model is a mechanism for comparing patterns. When patterns are fully generalized a natural definition of syntactic class emerges as a subset of relational class. These collocational syntactic classes should be an unambiguous partition of traditional syntactic classes.