Skip to main content
Book cover

Integration of World Knowledge for Natural Language Understanding

  • Book
  • © 2012

Overview

  • The detailed introduction to computational natural language understanding (NLU) helps the reader to obtain background knowledge necessary to perform practical NLU
  • The chapter on knowledge base construction shows how to obtain structured knowledge applicable to practical NLU from existing freely available knowledge resources
  • Includes a new algorithm for debugging inconsistent ontologies and a new methodology for ensuring conceptual consistency
  • Shows how heterogeneous knowledge can be employed in one single reasoning pipeline
  • Suggests practical application scenarios of the proposed approach
  • Includes supplementary material: sn.pub/extras

Part of the book series: Atlantis Thinking Machines (ATLANTISTM, volume 3)

This is a preview of subscription content, log in via an institution to check access.

Access this book

eBook USD 84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book USD 109.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Other ways to access

Licence this eBook for your library

Institutional subscriptions

Table of contents (9 chapters)

Keywords

About this book

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.

Authors and Affiliations

  • University of Osnabrück, Bremen, Germany

    Ekaterina Ovchinnikova

Bibliographic Information

Publish with us

Societies and partnerships