Co-Occurrence Cluster Features for Lexical Substitutions in Context
Chris Biemann · Workshop on Graph Based Methods for Natural Language Processing · 2010
This paper examines the influence of features based on clusters of co-occurrences for supervised Word Sense Disambiguation and Lexical Substitution. Co-occurrence cluster features are derived from clustering the local neighborhood of a target word in a co-occurrence graph based on a corpus in a completely unsupervised fashion. Clusters can be assigned in context and are used as features in a supervised WSD system. Experiments fitting a strong baseline system with these additional features are conducted on two datasets, showing improvements. Co-occurrence features are a simple way to mimic Topic Signatures (Martinez et al., 2008) without needing to construct resources manually. Further, a system is described that produces lexical substitutions in context with very high precision.