The ability to capture time information is
essential to many natural language processing
and information retrieval applications.
Therefore, a lexical resource associating
word senses to their temporal orientation
might be crucial for the computational
tasks aiming at the interpretation of
language of time in texts. In this paper,
we propose a semi-supervised minimum
cuts strategy that makes use of WordNet
glosses and semantic relations to supplement
WordNet entries with temporal information.
Intrinsic and extrinsic evaluations
show that our approach outperforms prior
semi-supervised non-graph classifiers.