Information Extraction (IE) systems that extract role fillers for events typically look at the local context surrounding a phrase when deciding whether to extract it. Often, however, role fillers occur in clauses that are not directly linked to an event word. We present a new model for event extraction that jointly considers both the local context around a phrase along with the wider sentential context in a probabilistic framework. Our approach uses a sentential event recognizer and a plausible role-filler recognizer that is conditioned on event sentences. We evaluate our system on two IE data sets and show that our model performs well in comparison to existing IE systems that rely on local phrasal context.
Patwardhan, S., & Riloff, E. (2009). A unified model of phrasal and sentential evidence for information extraction. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing Volume 1 - EMNLP ’09 (Vol. 1, p. 151). Morristown, NJ, USA: Association for Computational Linguistics. https://doi.org/10.3115/1699510.1699530