Modularizing Natural Language Processing
Tutorial, GTC 2020, New York, USA
Talks and presentations
Modularizing Natural Language Processing
Tutorial, AAAI 2020, New York, USA
Supervised Within-Document Event Coreference using Information Propagation
Talk, LREC 2014, Reykjavik, Iceland
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.