Premium Members Get 10% Off and Earn Rewards Find Out More
Naive Semantics for Natural Language Understanding
This book introduces a theory, Naive Semantics (NS), a theory of the knowledge underlying natural language understanding. The basic assumption of NS is that knowing what a word means is not very different from knowing anything else, so that there is no difference in form of cognitive representation between lexical semantics and ency­ clopedic knowledge. NS represents word meanings as commonsense knowledge, and builds no special representation language (other than elements of first-order logic). The idea of teaching computers common­ sense knowledge originated with McCarthy and Hayes (1969), and has been extended by a number of researchers (Hobbs and Moore, 1985, Lenat et aI, 1986). Commonsense knowledge is a set of naive beliefs, at times vague and inaccurate, about the way the world is structured. Traditionally, word meanings have been viewed as criterial, as giving truth conditions for membership in the classes words name. The theory of NS, in identifying word meanings with commonsense knowledge, sees word meanings as typical descriptions of classes of objects, rather than as criterial descriptions. Therefore, reasoning with NS representations is probabilistic rather than monotonic. This book is divided into two parts. Part I elaborates the theory of Naive Semantics. Chapter 1 illustrates and justifies the theory. Chapter 2 details the representation of nouns in the theory, and Chapter 4 the verbs, originally published as "Commonsense Reasoning with Verbs" (McDowell and Dahlgren, 1987). Chapter 3 describes kind types, which are naive constraints on noun representations.
1117268633
Naive Semantics for Natural Language Understanding
This book introduces a theory, Naive Semantics (NS), a theory of the knowledge underlying natural language understanding. The basic assumption of NS is that knowing what a word means is not very different from knowing anything else, so that there is no difference in form of cognitive representation between lexical semantics and ency­ clopedic knowledge. NS represents word meanings as commonsense knowledge, and builds no special representation language (other than elements of first-order logic). The idea of teaching computers common­ sense knowledge originated with McCarthy and Hayes (1969), and has been extended by a number of researchers (Hobbs and Moore, 1985, Lenat et aI, 1986). Commonsense knowledge is a set of naive beliefs, at times vague and inaccurate, about the way the world is structured. Traditionally, word meanings have been viewed as criterial, as giving truth conditions for membership in the classes words name. The theory of NS, in identifying word meanings with commonsense knowledge, sees word meanings as typical descriptions of classes of objects, rather than as criterial descriptions. Therefore, reasoning with NS representations is probabilistic rather than monotonic. This book is divided into two parts. Part I elaborates the theory of Naive Semantics. Chapter 1 illustrates and justifies the theory. Chapter 2 details the representation of nouns in the theory, and Chapter 4 the verbs, originally published as "Commonsense Reasoning with Verbs" (McDowell and Dahlgren, 1987). Chapter 3 describes kind types, which are naive constraints on noun representations.
169.99 In Stock
Naive Semantics for Natural Language Understanding

Naive Semantics for Natural Language Understanding

by Kathleen Dahlgren
Naive Semantics for Natural Language Understanding

Naive Semantics for Natural Language Understanding

by Kathleen Dahlgren

Overview

This book introduces a theory, Naive Semantics (NS), a theory of the knowledge underlying natural language understanding. The basic assumption of NS is that knowing what a word means is not very different from knowing anything else, so that there is no difference in form of cognitive representation between lexical semantics and ency­ clopedic knowledge. NS represents word meanings as commonsense knowledge, and builds no special representation language (other than elements of first-order logic). The idea of teaching computers common­ sense knowledge originated with McCarthy and Hayes (1969), and has been extended by a number of researchers (Hobbs and Moore, 1985, Lenat et aI, 1986). Commonsense knowledge is a set of naive beliefs, at times vague and inaccurate, about the way the world is structured. Traditionally, word meanings have been viewed as criterial, as giving truth conditions for membership in the classes words name. The theory of NS, in identifying word meanings with commonsense knowledge, sees word meanings as typical descriptions of classes of objects, rather than as criterial descriptions. Therefore, reasoning with NS representations is probabilistic rather than monotonic. This book is divided into two parts. Part I elaborates the theory of Naive Semantics. Chapter 1 illustrates and justifies the theory. Chapter 2 details the representation of nouns in the theory, and Chapter 4 the verbs, originally published as "Commonsense Reasoning with Verbs" (McDowell and Dahlgren, 1987). Chapter 3 describes kind types, which are naive constraints on noun representations.

Product Details

ISBN-13: 9781461284154
Publisher: Springer US
Publication date: 09/28/2011
Series: The Springer International Series in Engineering and Computer Science , #58
Edition description: Softcover reprint of the original 1st ed. 1988
Pages: 258
Product dimensions: 6.10(w) x 9.25(h) x 0.02(d)

Table of Contents

I. Naive Semantics.- 1. Naive Semantics.- 2. Noun Representation.- 3. Kinds, Kind Terms and Cognitive Categories.- 4. Verb Representation.- 5. The Functioning of the Kind Types System.- 6. Prepositional Phrase Disambiguation.- 7. Word Sense Disambiguation.- 8. Discourse Coherence.- References.
From the B&N Reads Blog
Page 1 of

Customer Reviews