A Thesis on Character Identification Open Access

Abstract

Traditional coreference resolution systems use methods insufficient for completely resolving 

plural mentions, especially when applying conventional coreference concepts to 

different tasks such as character identification. This paper gives a comprehensive view of 

one of the least examined yet most difficult parts of entity resolution–particularly coreference 

resolution and entity linking. Since our approach to entity resolution focuses on its 

applicability to character identification, we use the character identification corpus from 

SemEval 2018 and expand the dataset in scope to include plural mention annotations. We 

then show the inadequacy of these concepts and show an innovative design to overcome 

the shortcomings of traditional coreference ideas for the character identification task in 

this paper. Our innovative design includes an all-new algorithm for coreference resolution 

that selectively creates clusters to handle all types of mentions, singular and plural, as 

well as a new joint deep learning approach to entity linking determine the entities for both 

singular and plural mentions as well. Using our novel design, we demonstrate that our 

coreference and entity linking models surpass more traditional models. To the extent of 

what we know, we are the first to extensively investigate plural mentions in the context of 

entity resolution.

Table of Contents

Introduction Related Work Background Corpus Definitions Data Schema Annotation Crowdsourcing Quality Control Analytics Approach Coreference Resolution Algorithm Evaluation Metrics Entity Linking Multi-Task Learning Evaluation Metrics Experiments Configuration Coreference Resolution Entity Linking Conclusion References

About this Honors Thesis

Rights statement

• Permission granted by the author to include this thesis or dissertation in this repository. All rights reserved by the author. Please contact the author for information regarding the reproduction and use of this thesis or dissertation.

School	Emory College
Department	Mathematics and Computer Science
Degree	B.S.
Submission	Honors Thesis
Language	English
Research Field	Computer Science
Keyword	Identification Character
Committee Chair / Thesis Advisor	Choi, Jinho, Emory University
Committee Members	Tamasi, Susan, Emory University Cooper, Lee, Emory University

Last modified

Primary PDF

Thumbnail	Title	Date Uploaded	Actions
	A Thesis on Character Identification ()	2018-04-04 21:53:17 -0400	Press to Select an action Download

Supplemental Files

Thumbnail	Title	Date Uploaded	Actions