Understanding stories via event sequence modeling

Peng, Haoruo

Permalink

https://hdl.handle.net/2142/101526 Copy

Description

Title

Understanding stories via event sequence modeling

Author(s)

Peng, Haoruo

Issue Date

2018-07-03

Director of Research (if dissertation) or Advisor (if thesis)

Roth, Dan

Doctoral Committee Chair(s)

Roth, Dan

Committee Member(s)

• Hockenmaier, Julia
• Peng, Jian
• Gimpel, Kevin

Department of Study

Computer Science

Discipline

Computer Science

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

Ph.D.

Degree Level

Dissertation

Keyword(s)

• event sequence modeling
• event extraction
• entity co-reference
• event co-reference
• semantic language model
• discourse understanding

Abstract

Understanding stories, i.e. sequences of events, is a crucial yet challenging natural language understanding (NLU) problem, which requires dealing with multiple aspects of semantics, including actions, entities and emotions, as well as background knowledge. In this thesis, towards the goal of building a NLU system that can model what has happened in stories and predict what would happen in the future, we contribute on three fronts: First, we investigate the optimal way to model events in text; Second, we study how we can model a sequence of events with the balance of generality and specificity; Third, we improve event sequence modeling by joint modeling of semantic information and incorporating background knowledge. Each of the above three research problems poses both conceptual and computational challenges. For event extraction, we find that Semantic Role Labeling (SRL) signals can be served as good intermediate representations for events, thus giving us the ability to reliably identify events with minimal supervision. In addition, since it is important to resolve co-referred entities for extracted events, we make improvements to an existing co-reference resolution system. To model event sequences, we start from studying within document event co-reference (the simplest flow of events); and then extend to model two other more natural event sequences along with discourse phenomena while abstracting over the specific mentions of predicates and entities. We further identify problems for the basic event sequence models, where we fail to capture multiple semantic aspects and background knowledge. We then improve our system by jointly modeling frames, entities and sentiments, yielding joint representations of all these semantic aspects; while at the same time incorporate explicit background knowledge acquired from other corpus as well as human experience. For all tasks, we evaluate the developed algorithms and models on benchmark datasets and achieve better performance compared to other highly competitive methods.

Graduation Semester

2018-08

Type of Resource

text

Permalink

http://hdl.handle.net/2142/101526

Copyright and License Information

Copyright 2018 Haoruo Peng

Owning Collections