Integration of world knowledge for natural language understanding

Author(s)

    • Ovchinnikova, Ekaterina

Bibliographic Information

Integration of world knowledge for natural language understanding

Ekaterina Ovchinnikova

(Atlantis thinking machines / sereis editor, Kai-Uwe Kühnberger, v. 3)

Atlantis, c2012

  • : hardback
  • : softcover

Available at  / 3 libraries

Search this Book/Journal

Note

"Softcover reprint of the hardcover 1st edition 2012"--T.p. verso of softcover

Includes bibliographical references (p. 225-239) and index

Description and Table of Contents

Description

This book concerns non-linguistic knowledge required to perform computational natural language understanding (NLU). The main objective of the book is to show that inference-based NLU has the potential for practical large scale applications. First, an introduction to research areas relevant for NLU is given. We review approaches to linguistic meaning, explore knowledge resources, describe semantic parsers, and compare two main forms of inference: deduction and abduction. In the main part of the book, we propose an integrative knowledge base combining lexical-semantic, ontological, and distributional knowledge. A particular attention is payed to ensuring its consistency. We then design a reasoning procedure able to make use of the large scale knowledge base. We experiment both with a deduction-based NLU system and with an abductive reasoner. For evaluation, we use three different NLU tasks: recognizing textual entailment, semantic role labeling, and interpretation of noun dependencies.

Table of Contents

Preliminaries.- Natural Language Understanding and World Knowledge.- Sources of World Knowledge.- Reasoning for Natural Language Understanding.- Knowledge Base Construction.- Ensuring Consistency.- Abductive Reasoning with the Integrative Knowledge Base.- Evaluation.- Conclusion.

by "Nielsen BookData"

Related Books: 1-1 of 1

Details

  • NCID
    BB1062202X
  • ISBN
    • 9789491216527
    • 9789462390393
  • Country Code
    ne
  • Title Language Code
    eng
  • Text Language Code
    eng
  • Place of Publication
    Amsterdam
  • Pages/Volumes
    xvii, 242 p.
  • Size
    25 cm
  • Classification
  • Parent Bibliography ID
Page Top