MetaCart Sign in to MyCiteSeerX

Include Citations | Advanced Search | Help

Disambiguated Search | Include Citations | Advanced Search | Help

Tree-bank Grammars (1996) [171 citations — 2 self]

by Eugene Charniak ,  Eugene Charniak
In Proceedings of the Thirteenth National Conference on Artificial Intelligence
Add To MetaCart

Abstract:

By a "tree-bank grammar" 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 out-performs all other non-word-based statistical parsers/grammars on this corpus. That is, it out-performs parsers that consider the input as a string of tags and ignore the actual words of the corpus. 1 Introduction The simplest way to "learn" a context-free grammar from a parsed corpus (a "tree bank"), is to read the grammar off the parsed sentences. That is, if we have the sentence diagrammed in Figure 1 we can read the following rules off this diagram: S ! NP VP NP ! pron VP ! vb NP NP ! dt nn This r...

Citations

1196 Building a large annotated corpus of English: the penn treebank – Marcus, Marcinkiewicz, et al. - 1993
449 Statistical Language Learning – Charniak - 1997
260 Statistical Parsing with a ContextFree Grammar and Word Statistics – Charniak - 1997
239 Statistical decision-tree models for parsing – Magerman - 1995
200 Inside-outside reestimation from partially bracketed corpora – Pereira, Schabes - 1992
113 Automatic grammar induction and parsing free text: A transformationbased approach – Brill - 1993
53 New figures of merit for best-first probabilistic chart parsing – Caraballo, Charniak - 1998