Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/38796
Title: EVENT COREFERENCE RESOLUTION
Authors: CHEN BIN
Keywords: Event Coreference; Coreference Resolution; Natural Language Processing; Information Extraction; Machine Learning; Text Mining
Issue Date: 17-Aug-2012
Source: CHEN BIN (2012-08-17). EVENT COREFERENCE RESOLUTION. 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 thesis, we are the first in the literature providing a systematic and computation-oriented study on this challenging task. We present a global coreference-resolution system dedicated to sophisticated event coreference cases. First, seven resolvers are utilized to resolve different event and object Coreference pairs with new instance selection strategy and new linguistic features. Competing classifiers and topic-related event-detection are further imposed to enhance mention-pair resolvers. Second, two global solutions, spectral graph partitioning and random walk model, are employed for the chain formation. Spectral graph partitioning is equipped with heuristic-guidance and model specific manipulations to produce better coreference-chain results. Being the first attempt to apply random walk model for coreference resolution, the modified model utilizes a sampling method, termination criterion and stopping probability to greatly improve the effectiveness of random walk model for event coreference resolution. The new random walk 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. Collectively, all the above techniques impose significant B3 F-score improvement over baseline system on the OntoNotes4.0 Corpus.
URI: http://scholarbank.nus.edu.sg/handle/10635/38796
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
3.Event_Coreference_Resolution.pdf5.82 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

181
checked on Dec 11, 2017

Download(s)

108
checked on Dec 11, 2017

Google ScholarTM

Check


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