Paper: Inferring Sentence-Internal Temporal Relations

ACL ID N04-1020
Title Inferring Sentence-Internal Temporal Relations
Venue Human Language Technologies
Session Main Conference
Year 2004

In this paper we propose a data intensive ap- proach for inferring sentence-internal tempo- ral relations, which relies on a simple prob- abilistic model and assumes no manual cod- ing. We explore various combinations of fea- tures, and evaluate performance against a gold- standard corpus and human subjects perform- ing the same task. The best model achieves 70.7% accuracy in inferring the temporal rela- tion between two clauses and 97.4% accuracy in ordering them, assuming that the temporal relation is known.