Semantic Mapping for Lexical Sparseness Reduction in Parsing
Simon Šuster, Gertjan van Noord · University of Groningen research database (University of Groningen / Centre for Information Technology) · 2013
Bilexical information is known to be helpful in parse disambiguation, but the benefit is limited because of lexical sparseness. An approach us- ing word classes can reduce sparseness and po- tentially leads to more accurate parsing. Firstly, we describe a method identifying the depen- dency types of the Alpino parser for Dutch to which we would like to apply generaliza- tion. These are the types which are most likely to reduce the sparseness and positively affect parsing at the same time. Secondly, we provide preliminary results for enhancement of depen- dency types with semantic classes derived from a WordNet-like inventory for Dutch. Classes of varying degrees of generality are applied to three dependency types: nominal conjunc- tion, modification of adjective and modification of noun. We observe improvements in some concrete cases, whereas the overall parsing ac- curacy either remains unchanged or decreases. We identify drawbacks of human-built sense inventories, which provides motivation for a distributional semantic approach.