Supervised Within-Document Event Coreference using Information Propagation
16119Authors
nan
Abstract
AbstractEvent 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.
Keywords
Full Content
nan
Labeled Text
AbstractEvent 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.
Publication Details
- Paper ID:
- 16119
- Year:
- 2014
- Publication:
- TIPSTER
- Publication Type:
- conf
- DOI:
- nan