End-to-end Plural Coreference Resolution on TV Show Transcripts 公开

Abstract

This paper introduces the first plural end-to-end coreference resolution model. This coreference system generates spans embeddings, which are optimized to predict the mentions and the coreferent antecedents. This model handles plural mentions and plural speakers. Our approach builds on the higher-order coreference resolution with coarse-to-fine inference by adapting it to the Friends corpus, which has plural speakers as a feature and also has singletons. Additionally, the model predicts plural antecedents as done in previous plural coreference works. These, in combination with the singular antecedents, are used to construct the final clusters, which have a one-to-one correspondence to the entities.

Table of Contents

1         Introduction                                                                                                                1

2         Background                                                                                                                 3

2.1      Related Work                                                                                                            5

3          Approach                                                                                                                   12

3.1      Nested Mention Detection                                                                                   13

3.2      Plural Speakers                                                                                                       13

3.3      Singletons                                                                                                                14

3.4      Training Labels                                                                                                       15

3.5      Plural Coreference Resolution                                                                            16

3.6      Singularity                                                                                                               17

3.7      Merging Clusters                                                                                                    18

3.8      Many Antecedents with Upper Bounds                                                             19

3.9      Antecedent conflicts                                                                                             20

3.10   Alternate plural antecedents                                                                                21

4   Experiments                                                                                                                    23

5   Conclusion                                                                                                                       31

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	Computer Science
Degree	B.S.
Submission	Honors Thesis
Language	English
Research Field	Computer Science
关键词	Coreference Resolution NLP
Committee Chair / Thesis Advisor	Jinho Choi, Emory University
Committee Members	Robert Roth, Emory University James Lu, Emory University

最新修改

Primary PDF

Thumbnail	Title	Date Uploaded	Actions
	End-to-end Plural Coreference Resolution on TV Show Transcripts ()	2019-04-09 10:41:04 -0400	Press to Select an action Download

Supplemental Files

Thumbnail	Title	Date Uploaded	Actions