A Multilingual parallel parsed corpus as gold standard for grammatical inference evaluation

Menno van Zaanen, Andrew Roberts, Eric Atwell

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contribution

Abstract

In this article we investigate how (computational) grammar inference systems are evaluated and how the evaluation procedure can be improved. First, we describe the currently used evaluation methods and look at the advantages and disadvantages of each method. The main problems of the methods are: dependency on language experts, the influence of the annotation scheme of the language data, and the language dependency of the evaluation. We then propose a new method that will allow for an evaluation independently of language and annotation scheme. This method requires (syntactically) structured corpora in multiple languages to test for language independency of the grammatical inference system and corpora structured using different annotation schemes to diminish the influence the annotation has on the evaluation.
Original languageEnglish
Title of host publicationProceedings of The Amazing Utility of Parallel and Comparable Corpora Workshop held at the 4th International Language Resources and Evaluation Conference (LREC 2004)
Pages58-61
Number of pages4
Publication statusPublished - 2004
Externally publishedYes
EventThe Amazing Utility of Parallel and Comparable Corpora Workshop (2004) - Lisbon
Duration: 25 May 200425 May 2004

Workshop

WorkshopThe Amazing Utility of Parallel and Comparable Corpora Workshop (2004)
CityLisbon
Period25/05/0425/05/04

Fingerprint Dive into the research topics of 'A Multilingual parallel parsed corpus as gold standard for grammatical inference evaluation'. Together they form a unique fingerprint.

  • Cite this

    van Zaanen, M., Roberts, A., & Atwell, E. (2004). A Multilingual parallel parsed corpus as gold standard for grammatical inference evaluation. In Proceedings of The Amazing Utility of Parallel and Comparable Corpora Workshop held at the 4th International Language Resources and Evaluation Conference (LREC 2004) (pp. 58-61)