The work detailed in this paper describes a 2-step cascade approach for the classification of complex-type nominals. We describe an experiment that demonstrates how a cascade approach performs when the task consists in ...
The lexical semantic relationships between word pairs are key features for many NLP tasks. Most approaches for automatically classifying related word pairs are hindered by data sparsity because of their need to observe two ...
The work presented here depicts experiments toward the automatic classification of complex-type nominals using distributional information. We conducted two experiments: classifying complex-type nominals as members of ...
Acquiring lexical information is a complex problem, typically approached by relying on a number of contexts to contribute information for classification. One of the first issues to address in this domain is the determination ...
The work presented here addresses the use of unmarked contexts in pattern-based nominal lexical semantic classification. We define unmarked contexts to be the counterposition of the class-indicatory, or marked, contexts. ...
