Supervised Within-Document Event Coreference using Information Propagation

Zhengzhong Liu, Jun Araki, Eduard H. Hovy, Teruko Mitamura

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.
BibTeX
@inproceedings{liu2014supervised,
  author = {Zhengzhong Liu and Jun Araki and Eduard H. Hovy and Teruko Mitamura},
  title = {{Supervised Within-Document Event Coreference using Information Propagation}},
  booktitle = {LREC},
  year = {2014},
  url = {https://openreview.net/forum?id=O-oWhDb4je9},
}

Loading related content...

Figure