Identifying Temporal Orientation of Word Senses Based on Minimum Cuts
Résumé
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.