Contact Us

Instructions

Frequently Asked Questions

ETD Help

Policies and Procedures

Copyright and Patents

Access Restrictions

Search ETDs:
Advanced Search
Browse by:
Browse ProQuest
Search ProQuest

Laney Graduate School

Rollins School of Public Health

Candler School of Theology

Emory College

Emory Libraries

New ETD website is now LIVE and located here: etd.library.emory.edu

Character Identification on Multi-party Dialogues

Chen, Yu-Hsin (Henry) (2017)
Honors Thesis (65 pages)
Committee Chair / Thesis Adviser: Choi, Jinho
Committee Members: Lu, James ; Julien, Heather F
Research Fields: Computer science; Artificial intelligence
Keywords: Natural Language Processing; Character Identification; Dialogue Processing; Entity Linking; Coreference Resolution; Corpus Creation
Program: College Honors Program, Computer Science
Permanent url: http://pid.emory.edu/ark:/25593/rxf6s

Abstract

This thesis introduces a subtask of entity linking, called character identification, that maps mentions in multiparty conversation to their referent characters. Transcripts of TV shows are collected as the sources of our corpus and automatically annotated with mentions by linguistically-motivated rules. These mentions are manually linked to their referents and disambiguate with abstract referent labels through crowdsourcing. Our annotated corpus comprises 448 scenes from 2 seasons and 46 episodes of the TV show Friends, and shows the inter-annotator agreement of κ = 79.96. For statistical modeling, this task is reformulated as coreference resolution, and experimented with two state-of-the-art systems on our corpus. A novel mention-to-mention ranking model is proposed to provides better mention and mention-pair representations learned from feature groupings of dialogue-specific features After linking coreferent clusters to their referent entity with our proposed rule-based remapping algorithm, the best model gives a purity score of 57.27% on average, which is promising given the challenging nature of this task and our corpus.

Table of Contents

1 Introduction
1.1 Task definition
1.2 Motivation
1.3 Objectives
2 Background
2.1 Entity linking
2.2 Speaker identification
2.3 Conversation Corpora
2.4 Neural network
2.4.1 Word2Vec and Word Embeddings
2.4.2 Convolutional Neural Network
2.5 Coreference resolution
2.5.1 Evaluation Metrics
2.5.2 Stanford Sieve System
2.5.3 Stanford Neural System
2.5.4 Harvard Neural System
3 Corpus
3.1 Corpus creation
3.1.1 Data collection
3.1.2 Mention detection
3.1.3 Corpus annotation
3.1.4 Corpus adjudication
3.1.5 Corpus disambiguation
3.2 Corpus analysis
3.2.1 Annotation results
3.2.2 Mention Detection Error
3.2.3 Annotation Disagreement
4 Approaches
4.1 Data Formulation
4.1.1 Data Split
4.1.2 Data formats
4.2 Coreference resolution
4.2.1 CNN mention-to-mention model
4.3 Character identification
4.3.1 Rule-based entity linker
5 Experiments
5.1 Task analysis
5.1.1 Task feasibility
5.1.2 Rule-based vs. statistical model
5.1.3 Episode-delim vs. scene-delim documents
5.1.4 Learning past vs. future conversations
5.2 Coreference resolution
5.2.1 Stanford neural system
5.2.2 Harvard neural system
5.2.3 CNN mention-to-mention ranking model
5.3 Character identification
5.3.1 Linking rules
5.3.2 Cluster remapping
6 Conclusion

Files

application/pdf Honors Thesis 65 pages (1.3 MB) [Access copy of Honors Thesis]
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.