Aston Logo


Postgraduate Conference Home
Presentations and Posters

Tom Richens (Aston University)

Enhancing Wordnet by parsing usage examples and corpus data


A model of WordNet developed at Aston University has shown up taxonomic inconsistencies (Richens 2008), inconsistencies with regard to the representation of verb alternations and verb frame inaccuracies. All the examples illustrating verb usages have been parsed to generate an empirically-based set of verb frames. The current phase of this research involves parsing the British National Corpus to validate the verb frames and discover new ones, and to determine their comparative frequencies. The data generated will be mapped onto a coarser-grained version of WordNet generated by the application of recognised clustering algorithms (Mihalcea & Moldovan, 2001).

The anticipated outcome will be an empirically-proven resource akin to Hank's (2008) Pattern Dictionary, only organised by meanings. This is expected to compare favourably with VerbNet (another Lexical Database based on Levin's (1993) Verb Classes), which has never been validated against corpus data. The new model will be able to inform a reorganisation of the verb taxonomy, applying principles of verb frame inheritance as suggested by Amaro et al. (2006).

Amaro, R., Chaves, R. P., Marrafa, P. & Mendes S. (2006). Enriching Wordnets with new Relations and with Event and Argument Structures. In: Seventh International Conference on Intelligent Text Processing and Computational Linguistics, Mexico City, 19-25 Feb. 2006, 28 - 40.
Hanks, P. (2008). The Lexicographical Legacy of John Sinclair, International Journal of Lexicography, Vol. 21, No. 3, Oxford University Press.
Levin, B. (1993). English verb Classes and Alternations: A Preliminary Investigation, Chicago, University of Chicago Press.
Mihalcea, R. & Moldovan, D. (2001). Automatic Generation of a Coarse Grained WordNet, Proceedings of NAACL Workshop on WordNet and Other Lexical Resources, Pittsburgh, PA, 2-7 June, 2001.
Richens T. (2008). Anomalies in the WordNet Verb Hierarchy, Proceedings of the 22nd International Conference on Computational Linguistics , Manchester, 18-22 August, 2008.

L10 Web Stats Reporter 3.15 LevelTen Hit Counter - Free PHP Web Analytics Script
LevelTen dallas web development firm - website design, flash, graphics & marketing