Integration of World Knowledge for Natural Language Understanding (Atlantis Thinking Machines, Band 3) - Softcover

Ovchinnikova, Ekaterina

Softcover

ISBN 10: 9462390398 ISBN 13: 9789462390393

Verlag: Atlantis Press, 2014

Inhaltsangabe

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.

Über diesen Titel

Von der hinteren Coverseite

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.

Details zur Ausgabe

• Verlag: Atlantis Press
• Erscheinungsdatum: 2014
• Sprache: Englisch
• ISBN 10: 9462390398
• ISBN 13: 9789462390393
• Einband: Taschenbuch
• Anzahl der Seiten: 264
• Kontakt zum Hersteller: Dt. Universitätsverlag; buchhandel-buch@springer.com; ; Abraham-Lincoln-Str. 46; Wiesbaden; 65198; Deutschland