Learning grammars for different parsing tasks by partition search

Research output: Chapter in Book/Conference proceeding with ISSN or ISBNConference contribution with ISSN or ISBN

Abstract

This paper describes a comparative application of Grammar Learning by Partition Search to four different learning tasks: deep parsing, NP identification, flat phrase chunking and NP chunking. In the experiments, base grammars were extracted from a treebank corpus. From this starting point, new grammars optimised for the different parsing tasks were learnt by Partition Search. No lexical information was used. In half of the experiments, local structural context in the form of parent phrase category information was incorporated into the grammars. Results show that grammars which contain this information outperform grammars which do not by large margins in all tests for all parsing tasks. It makes the biggest difference for deep parsing, typically corresponding to an improvement of around 5%. Overall, Partition Search with parent phrase category information is shown to be a successful method for learning grammars optimised for a given parsing task, and for minimising grammar size. The biggest margin of improvement over a base grammar was a 5.4% increase in the F-Score for deep parsing. The biggest size reductions were 93.5% fewer nonterminals (for NP identification), and 31.3% fewer rules (for XP chunking)
Original languageEnglish
Title of host publicationCOLING '02 Proceedings of the 19th international conference on computational linguistics
Place of PublicationStroudsbury, PA, USA
PublisherAssociation for Computational Linguistics
Pages78-84
Number of pages7
Volume1
ISBN (Print)1558608958
DOIs
Publication statusPublished - 1 Jan 2002
EventCOLING '02 Proceedings of the 19th international conference on computational linguistics - Taipei, Taiwan
Duration: 1 Jan 2002 → …

Conference

ConferenceCOLING '02 Proceedings of the 19th international conference on computational linguistics
Period1/01/02 → …

Bibliographical note

Association for Computational Linguistics Stroudsburg, PA, USA © 2002

Fingerprint Dive into the research topics of 'Learning grammars for different parsing tasks by partition search'. Together they form a unique fingerprint.

  • Cite this

    Belz, A. (2002). Learning grammars for different parsing tasks by partition search. In COLING '02 Proceedings of the 19th international conference on computational linguistics (Vol. 1, pp. 78-84). Association for Computational Linguistics. https://doi.org/10.3115/1072228.1072296