Krotov, A., Hepple, M., Gaizauskas, R. and Wilks, Y. (1999) Evaluating two methods for Treebank grammar compaction. Natural Language Engineering, 5 (4). pp. 377-394. ISSN 1351-3249Full text available as:
Treebanks, such as the Penn Treebank, provide a basis for the automatic creation of broad coverage grammars. In the simplest case, rules can simply be ‘read off’ the parse-annotations of the corpus, producing either a simple or probabilistic context-free grammar. Such grammars, however, can be very large, presenting problems for the subsequent computational costs of parsing under the grammar.
In this paper, we explore ways by which a treebank grammar can be reduced in size or ‘compacted’, which involve the use of two kinds of technique: (i) thresholding of rules by their number of occurrences; and (ii) a method of rule-parsing, which has both probabilistic and non-probabilistic variants. Our results show that by a combined use of these two techniques, a probabilistic context-free grammar can be reduced in size by 62% without any loss in parsing performance, and by 71% to give a gain in recall, but some loss in precision.
|Copyright, Publisher and Additional Information:||© 1999 Cambridge University Press. Reproduced in accordance with the publisher's self-archiving policy.|
|Institution:||The University of Sheffield|
|Academic Units:||The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield)|
|Depositing User:||Repository Assistant|
|Date Deposited:||03 Oct 2006|
|Last Modified:||05 Jun 2014 12:37|
|Publisher:||Cambridge University Press|