Abstract | ||
---|---|---|
This paper presents a novel approach to the task of semantic role labelling for event nominalisations, which make up a considerable fraction of predicates in running text, but are underrepresented in terms of training data and difficult to model. We propose to address this situation by data expansion. We construct a model for nominal role labelling solely from verbal training data. The best quality results from salvaging grammatical features where applicable, and generalising over lexical heads otherwise. |
Year | Venue | Keywords |
---|---|---|
2008 | COLING | best quality result,novel approach,training data,considerable fraction,verbal training data,data expansion,event nominalisations,nominal role,semantic role assignment,grammatical feature,semantic role,verbal data |
Field | DocType | Volume |
Training set,Computer science,Semantic role labelling,Labelling,Natural language processing,Artificial intelligence,Predicate (grammar) | Conference | C08-1 |
Citations | PageRank | References |
17 | 1.01 | 18 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sebastian Padó | 1 | 1787 | 146.15 |
Marco Pennacchiotti | 2 | 1742 | 84.81 |
Caroline Sporleder | 3 | 453 | 31.84 |