Naive semantics for natural language understanding
著者
書誌事項
Naive semantics for natural language understanding
(The Kluwer international series in engineering and computer science, SEC 58 . Natural language processing and machine translation)
Kluwer Academic Publishers, c1988
大学図書館所蔵 全21件
  青森
  岩手
  宮城
  秋田
  山形
  福島
  茨城
  栃木
  群馬
  埼玉
  千葉
  東京
  神奈川
  新潟
  富山
  石川
  福井
  山梨
  長野
  岐阜
  静岡
  愛知
  三重
  滋賀
  京都
  大阪
  兵庫
  奈良
  和歌山
  鳥取
  島根
  岡山
  広島
  山口
  徳島
  香川
  愛媛
  高知
  福岡
  佐賀
  長崎
  熊本
  大分
  宮崎
  鹿児島
  沖縄
  韓国
  中国
  タイ
  イギリス
  ドイツ
  スイス
  フランス
  ベルギー
  オランダ
  スウェーデン
  ノルウェー
  アメリカ
注記
Bibliography: p. [231]-249
Includes index
内容説明・目次
内容説明
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 represen tations 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.
目次
I. Naive Semantics.- 1. Naive Semantics.- 1.1. Using Naive Semantics to Interpret "The Programmer".- 1.2. Compositional Semantics.- 1.3. The Classical Theory of Word Meaning.- 1.4. Word Meanings as Concepts.- 1.5. Other Decompositional Approaches.- 1.6. Computational Approaches to Word Meaning.- 1.7. Naive Semantics.- 1.8. Basis of Naive Semantics in Cognitive Psychology.- 1.9. Comparison of NS with Computational Models.- 1.10. Limitations of NS.- 1.11. Organization of the Book.- 2. Noun Representation.- 2.1. The Ontological Schema.- 2.2. Mathematical Properties of the Ontology.- 2.3. Ontological Categories.- 2.4. Nominal Terminal Nodes.- 2.5. Construction of the Ontology.- 2.6. Other Ontologies.- 2.7. Generic Knowledge.- 2.8. Word Senses.- 2.9. Feature Types.- 2.10. Conclusion.- 3. Kinds, Kind Terms and Cognitive Categories.- 3.1. The Realist Basis of NS and Kind Terms.- 3.2. Kind Types.- 3.3. Kind Types as Metasorts.- 3.4. Another Approach.- 3.5. Summary.- 4. Verb Representation.- 4.1. Ontological Representation.- 4.2. Placing Verbs in the Main Ontology.- 4.3. Sub-Classification of the TEMPORAL/RELATIONAL Node.- 4.4. The Vendler Verb Classification.- 4.5. Psycholinguistic Categories.- 4.6. Cross-Classification.- 4.7. Parallel Ontologies.- 4.8. Non-Categorial Features.- 4.9. Generic Representation.- 4.10. Feature Types Associated with Relational Terms.- 4.11. Conclusion.- 5. The Functioning of the Kind Types System.- 5.1. Complete and Incomplete Knowledge.- 5.2. Queries to the System.- Inspecting the Textual Database.- Inspecting the Ontology.- Inspecting the Generic Database.- Inspecting Feature Types.- 5.3. Anaphors.- 5.4. PP Attachment.- 5.5. Word Sense Disambiguation.- 5.6. Discourse Reasoning.- 5.7. Kind Types Reasoning.- 5.8. Summary of Inference Mechanism.- 6. Prepositional Phrase Disambiguation.- 6.1. Semantically Implausible Syntactic Ambiguities.- 6.2. Using Commonsense Knowledge to Disambiguate.- 6.3. Commonsense Knowledge used in the Preference Strategy.- Ontological Class of Object of the Preposition.- Ontological Class of The Direct Object.- Ontological Class of Verb.- Generic Information.- Syntax.- 6.4. Success Rate of the Preference Strategy.- 6.5. Implementation.- 6.6. Other Approaches.- 6.7. Conclusion.- 7. Word Sense Disambiguation.- 7.1. Approaches to Word Sense Disambiguation.- 7.2. Local Combined Ambiguity Reduction.- 7.3. Test of Hypothesis.- 7.4. Noun Disambiguation.- Fixed and Frequent Phrases.- Syntactic Tests.- Commonsense Knowledge.- 7.5. Verb Sense Disambiguation.- Frequent Phrases in Verb Disambiguation.- Syntactic Tests in Verb Disambiguation.- Commonsense in Verb Disambiguation.- 7.6. Interaction of Ambiguous Verb and Noun.- 7.7. Feasibility of the Method.- 7.8. Syntactic and Lexical Ambiguity.- 7.9. Intersentential Reasoning.- 7.10. Disambiguation Rules.- 7.11. Efficiency and Timing.- 7.12. Problems for the Method.- 7.13. Other Approaches.- 7.14. Conclusion.- 8. Discourse Coherence.- 8.1. Background.- Coherence Relations.- Discourse Segments.- Genre-Relativity of Discourse Structure.- The Commentary Genre.- Compendium of Discourse Relations.- 8.2. Modularity and Discourse.- Modelling the Recipient.- Discourse Events.- Coherence as Compositional Semantics?.- Coherence as Naive Inference.- Discourse Cues.- Parallelism.- Facts Explained by the Parallel, Modular Model.- 8.3. Syntactic and Semantic Tests for Discourse Relations.- Main Clause.- Not Nominalized.- Active voice.- Tense and Aspect.- Transitivity Test.- Weak Predictions of Coherence Relations.- 8.4. Parallelism in Coherence Exemplified.- Using Commonsense Knowledge to Segment Discourse.- Empirical Study of Discourse Hierarchy.- 8.5. Other Models.- 8.6. Conclusion.- References.
「Nielsen BookData」 より