Please use this identifier to cite or link to this item:
Title: Random walks down the mention graphs for event coreference resolution
Authors: Chen, B.
Su, J.
Tan, C.L. 
Keywords: Anaphora resolution
Competing classifiers
Coreference resolution
Event coreference
Instance selection
Random walks partitioning
Self-interacting walks
Issue Date: 2013
Citation: Chen, B., Su, J., Tan, C.L. (2013). Random walks down the mention graphs for event coreference resolution. ACM Transactions on Intelligent Systems and Technology 4 (4) : -. ScholarBank@NUS Repository.
Abstract: Event coreference is an important task in event extraction and other natural language processing tasks. Despite its importance, it was merely discussed in previous studies. In this article, we present a global coreference resolution system dedicated to various sophisticated event coreference phenomena. First, seven resolvers are utilized to resolve different event and object coreferencemention pairs with a new instance selection strategy and new linguistic features. Second, a global solution-a modified random walk partitioning-is employed for the chain formation. Being the first attempt to apply the random walk model for coreference resolution, the revised model utilizes a sampling method, termination criterion, and stopping probability to greatly improve the effectiveness of random walk model for event coreference resolution. Last but not least, the new model facilitates a convenient way to incorporate sophisticated linguistic constraints and preferences, the related object mention graph, as well as pronoun coreference information not used in previous studies for effective chain formation. In total, these techniques impose more than 20% F-score improvement over the baseline system. © 2013 ACM.
Source Title: ACM Transactions on Intelligent Systems and Technology
ISSN: 21576904
DOI: 10.1145/2508037.2508055
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

checked on Dec 29, 2018

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.