Understanding time in natural language text

Ning, Qiang

Permalink

https://hdl.handle.net/2142/106211 Copy

Description

Title

Understanding time in natural language text

Author(s)

Ning, Qiang

Issue Date

2019-12-02

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

Roth, Dan

Doctoral Committee Chair(s)

Roth, Dan

Committee Member(s)

• Hasegawa-Johnson, Mark
• Hockenmaier, Julia
• Hwu, Wen-Mei
• Palmer, Martha

Department of Study

Electrical & Computer Eng

Discipline

Electrical & Computer Engr

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

Ph.D.

Degree Level

Dissertation

Keyword(s)

• Natural language processing
• Event
• Time
• Temporal relation
• Temporal common sense
• Incidental supervision

Abstract

Understanding time is essential to understanding events in the world. Knowing what has happened, what is happening, and what may happen in the future is critical for reasoning about those events. It is thus an important natural language processing (NLP) task to understand time. This thesis advances the study of time by developing new insights into some aspects of the problem of reasoning about time in text, new algorithmic and machine learning approaches, and new datasets that would support continuing work on these problems by the research community. We also discuss a few research directions suggested by this work that could further improve our understanding of time in natural language text. The thesis specifically addresses three key aspects of the temporal reasoning problem: time expression understanding, temporal relation extraction, and temporal common sense acquisition. Time expressions (e.g., yesterday or last month) often provide absolute time anchors for events. Temporal relations (e.g., event A is before or after event B) provide relative order information between events, which is complementary to time expressions. Temporal common sense (e.g., duration and frequency) is another important component in temporal reasoning, but is usually absent in a single piece of text because people do not say things that are obvious. The bulk of this thesis is devoted to the important problem of identifying temporal relations between events, a problem that has been studied a lot by the research community. The work in the thesis introduces new machine learning methods and a novel conceptual view of the problem that together result in an improvement of more than 20% over the previous state-of-the-art.

Graduation Semester

2019-12

Type of Resource

text

Permalink

http://hdl.handle.net/2142/106211

Copyright and License Information

Copyright 2019 Qiang Ning

Owning Collections