© 2012

Integration of World Knowledge for Natural Language Understanding


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

Table of contents

  1. Front Matter
    Pages i-xvii
  2. Ekaterina Ovchinnikova
    Pages 1-14
  3. Ekaterina Ovchinnikova
    Pages 15-37
  4. Ekaterina Ovchinnikova
    Pages 39-71
  5. Ekaterina Ovchinnikova
    Pages 73-92
  6. Ekaterina Ovchinnikova
    Pages 93-122
  7. Ekaterina Ovchinnikova
    Pages 123-154
  8. Ekaterina Ovchinnikova
    Pages 155-175
  9. Ekaterina Ovchinnikova
    Pages 177-214
  10. Ekaterina Ovchinnikova
    Pages 215-220
  11. Back Matter
    Pages 221-242

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.


Lexical-semantic resources Natural language understanding Ontologies Reasoning Weighted abduction

Authors and affiliations

  1. 1.University of OsnabrückBremenGermany

Bibliographic information

Industry Sectors
IT & Software