Decreasing lexical data sparsity in statistical syntactic parsing - experiments with named entities
Hogan, Deirdre and Foster, Jennifer and Van Genabith, Josef (2011) Decreasing lexical data sparsity in statistical syntactic parsing - experiments with named entities. In: Multiword Expressions: from Parsing and Generation to the Real World (MWE). Workshop at ACL 2011, 19-24 June 2011, Portland, Oregon.
Full text available as:
In this paper we present preliminary experiments that aim to reduce lexical data sparsity in statistical parsing by exploiting information about named entities. Words in the
WSJ corpus are mapped to named entity clusters and a latent variable constituency parser is trained and tested on the transformed corpus. We explore two different methods for
mapping words to entities, and look at the effect of mapping various subsets of named entity types. Thus far, results show no improvement in parsing accuracy over the best baseline score; we identify possible problems and outline suggestions for future directions.
Archive Staff Only: edit this record