Integration of World Knowledge for Natural Language Understanding

• Κύριος συγγραφέας: Ovchinnikova, Ekaterina (Συγγραφέας)
• Συγγραφή απο Οργανισμό/Αρχή: SpringerLink (Online service)
• Μορφή: Ηλεκτρονική πηγή Ηλ. βιβλίο
• Γλώσσα: English
• Έκδοση: Paris : Atlantis Press, 2012.
• Σειρά: Atlantis Thinking Machines, 3
• Θέματα: Computer science.; Mathematical logic.; Computers.; Artificial intelligence.; Text processing (Computer science).; Computational linguistics.; Computer Science.; Language Translation and Linguistics.; Artificial Intelligence (incl. Robotics).; Mathematical Logic and Formal Languages.; Document Preparation and Text Processing.; Computing Methodologies.

 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. 

 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.