Identifying Temporal Orientation of Word Senses

Mohammed Hasanuzzaman1, Gaël Dias2, Stéphane Ferrari2, Yann Mathet2, Andy Way3
1ADAPT Centre, Dublin, Ireland, 2Université de Caen Normandie, 3ADAPT Centre, School of Computing, Dublin City University


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.