Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Tree-bank grammars

Conference ·
OSTI ID:430779
 [1]
  1. Brown Univ., Providence, RI (United States)

By a {open_quotes}tree-bank grammar{close_quotes} we mean a context-free grammar created by reading the production rules directly from hand-parsed sentences in a tree bank. Common wisdom has it that such grammars do not perform well, though we know of no published data on the issue. The primary purpose of this paper is to show that the common wisdom is wrong. In particular, we present results on a tree-bank grammar based on the Penn Wall Street Journal tree bank. To the best of our knowledge, this grammar outperforms all other non-word-based statistical parsers/grammars on this corpus. That is, it outperforms parsers that consider the input as a string of tags and ignore the actual words of the corpus.

OSTI ID:
430779
Report Number(s):
CONF-960876--
Country of Publication:
United States
Language:
English

Similar Records

Parallel parsing of tree adjoining grammars on the connection machine
Journal Article · Fri Jan 31 23:00:00 EST 1992 · International Journal of Parallel Programming; (United States) · OSTI ID:7249394

Generalized queries on probabilistic context-free grammars
Conference · Mon Dec 30 23:00:00 EST 1996 · OSTI ID:430816

Generalized augmented transition network grammars for generation from semantic networks
Journal Article · Thu Dec 31 23:00:00 EST 1981 · Am. J. Comput. Ling.; (United States) · OSTI ID:6412706