Georgetown University LogoGeorgetown University Library LogoDigitalGeorgetown Home
    • Login
    View Item 
    •   DigitalGeorgetown Home
    • Georgetown University Institutional Repository
    • Georgetown College
    • Department of Linguistics
    • Graduate Theses and Dissertations - Linguistics
    • View Item
    •   DigitalGeorgetown Home
    • Georgetown University Institutional Repository
    • Georgetown College
    • Department of Linguistics
    • Graduate Theses and Dissertations - Linguistics
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    A Hybrid Approach to Inferring a Consistent Temporal Relation Set in Natural Language Text

    Cover for A Hybrid Approach to Inferring a Consistent Temporal Relation Set in Natural Language Text
    View/Open
    View/Open: Lee_georgetown_0076D_12325.pdf (1.1MB) Bookview

    Creator
    Lee, Chong Min
    Advisor
    Katz, Graham E
    Abstract
    This dissertation investigates the temporal relation identification
     
    task. The goal is to construct consistent temporal relations between
     
    temporal entities (e.g., events and time expressions) in a
     
    narrative. Constructing consistent temporal relations is challenging
     
    due to the exponential increase in the number of candidates for
     
    temporal relations proportional to the number of pairs of temporal
     
    entities. When we use transitive constraints to construct consistent
     
    temporal relations, performance improvement can be expected because
     
    the application of transitive constraints reduces the number of
     
    possible relation candidates in a narrative.
     
    The primary objective of this study is to develop a temporal relation
     
    identification (TRI) system that is composed of three modules: 1) a
     
    module that classifies the temporal relation of a pair of temporal
     
    entities, 2) a module that extracts conflicting classified relations
     
    using transitive constraints, and 3) a module that restores consistent
     
    temporal relations from the conflicting relations using transitive
     
    constraints. In developing a TRI system, this dissertation examines
     
    whether the application of transitive constraints to such a system can
     
    lead to performance improvement.
     
    The first step in developing the system was to implement a rudimentary
     
    temporal relation classification module. The module labels a pair of
     
    temporal entities with a temporal relation among eleven possible
     
    temporal relations. Next, a method for extracting conflicting
     
    relations among classified relations is proposed. The extraction
     
    method is based on heuristics because of NP-hard complexity in
     
    extracting all conflicting relations. Finally, two heuristic methods
     
    are proposed that restore consistent temporal structure from
     
    conflicting relations using transitive constraints. The performance of
     
    the developed system is tested using TimeBank and AQUAINT temporal
     
    corpora.
     
    The results of this work indicate that a performance improvement
     
    through the application of transitive constraints to TRI task is not
     
    guaranteed. Furthermore, this study empirically shows the limitations
     
    on performance improvement through the application of transitive
     
    constraints to the TRI task and identifies the bottlenecks in the TRI
     
    task.
     
    Description
    Ph.D.
    Permanent Link
    http://hdl.handle.net/10822/559494
    Date Published
    2013
    Subject
    computational linguistics; natural language processing; temporal information processing; temporal relation classification; temporal relation extraction; temporal relation identification; Linguistics; Computer science; Linguistics; Computer science;
    Type
    thesis
    Publisher
    Georgetown University
    Extent
    203 leaves
    Collections
    • Graduate Theses and Dissertations - Linguistics
    Metadata
    Show full item record

    Related items

    Showing items related by title, author, creator and subject.

    • Cover for Inferred Propositions and the Expression of the Evidence Relation in  Natural Language: Evidentiality in Central Alaskan Yup'ik Eskimo and English

      Inferred Propositions and the Expression of the Evidence Relation in Natural Language: Evidentiality in Central Alaskan Yup'ik Eskimo and English 

      Krawczyk, Elizabeth Allyn (Georgetown University, 2012)
      <italic>Evidentiality</italic> has usually been defined as the grammaticalized expression
    Related Items in Google Scholar

    Georgetown University Seal
    ©2009 - 2022 Georgetown University Library
    37th & O Streets NW
    Washington DC 20057-1174
    202.687.7385
    digitalscholarship@georgetown.edu
    Accessibility
     

     

    Browse

    All of DigitalGeorgetownCommunities & CollectionsCreatorsTitlesBy Creation DateThis CollectionCreatorsTitlesBy Creation Date

    My Account

    Login

    Statistics

    View Usage Statistics

    Georgetown University Seal
    ©2009 - 2022 Georgetown University Library
    37th & O Streets NW
    Washington DC 20057-1174
    202.687.7385
    digitalscholarship@georgetown.edu
    Accessibility