Supervised Within-Document Event Coreference using Information Propagation

Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC 2014)

Abstract

Event coreference is an important task for full text analysis. However, previous work uses a variety of approaches, sources and evaluation, making the literature confusing and the results incommensurate. We provide a description of the differences to facilitate future research. Second, we present a supervised method for event coreference resolution that uses a rich feature set and propagates information alternatively between events and their arguments, adapting appropriately for each type of argument.