Metaphor. Tony VealeЧитать онлайн книгу.
University of Cambridge
Beata Beigman Klebanov
Educational Testing Service
SYNTHESIS LECTURES ON HUMAN LANGUAGE TECHNOLOGIES #31
ABSTRACT
The literary imagination may take flight on the wings of metaphor, but hard-headed scientists are just as likely as doe-eyed poets to reach for a metaphor when the descriptive need arises. Metaphor is a pervasive aspect of every genre of text and every register of speech, and is as useful for describing the inner workings of a “black hole” (itself a metaphor) as it is the affairs of the human heart. The ubiquity of metaphor in natural language thus poses a significant challenge for Natural Language Processing (NLP) systems and their builders, who cannot afford to wait until the problems of literal language have been solved before turning their attention to figurative phenomena. This book offers a comprehensive approach to the computational treatment of metaphor and its figurative brethren—including simile, analogy, and conceptual blending—that does not shy away from their important cognitive and philosophical dimensions. Veale, Shutova, and Beigman Klebanov approach metaphor from multiple computational perspectives, providing coverage of both symbolic and statistical approaches to interpretation and paraphrase generation, while also considering key contributions from philosophy on what constitutes the “meaning” of a metaphor. This book also surveys available metaphor corpora and discusses protocols for metaphor annotation. Any reader with an interest in metaphor, from beginning researchers to seasoned scholars, will find this book to be an invaluable guide to what is a fascinating linguistic phenomenon.
KEYWORDS
metaphor, simile, analogy, blending, figurative language processing
Contents
2 Computational Approaches to Metaphor: Theoretical Foundations
2.1 The What, Why and How of Metaphor
2.5.1 Domain Representations in Metaphor and Analogy
2.6 Conceptual Metaphor Theory
2.7 Conceptual Integration and Blending
2.8 An Integrated Perspective
3 Artificial Intelligence and Metaphor
3.1 Corrective Approaches: Metaphor Diagnosis and Repair
3.2 Analogical Approaches: Mapping Meanings between Domains
3.3 Schematic Approaches: Families of Metaphor
3.4 Common Themes and Future Prospects
4.1 Metaphor Identification in Corpus Linguistics
4.2 The MIP Overall
4.3 Specifications of Auxiliary Concepts
4.3.1 Sense Inventories
4.3.2 Criterion for Sense Distinctiveness
4.3.3 Lexical Unit
4.4 The MIP in Languages other than English
4.5 Annotated Datasets
4.5.1 Categorized Collections of Metaphors
4.5.2 Annotations of Specific Constructions or Target expressions
4.5.3 Full-Text Annotations
4.5.4 Summary of Annotated Data Available for Public or License-Based Use
4.5.5 Additional Annotated Materials
5 Knowledge Acquisition and Metaphor
5.1 WordNet and other Lexical Ontologies
5.2 Extracting Knowledge from Free Text
5.2.1 Simile Patterns
5.2.2 Categorization Patterns
5.2.3 Arbitrary Relations
5.3 Conceptual Metaphors
5.4 Summary
6 Statistical Approaches to Metaphor
6.1 Association Measures and Selectional Preferences
6.2 Supervised Classification
6.3 Clustering
6.4 The Topical Structure of Text
6.5 Vector Space Models
6.6 Concreteness
7 Applications of Metaphor Processing
7.1 Metaphor in Culture, Communication, and Education
7.1.1 Common Metaphors in Cultures and Discourse Communities
7.1.2 Metaphor as a Framing Device in Political Communication
7.1.3 Metaphor Comprehension and Use as a Skill
7.2 Creativity Applications in NLP
7.2.1 Creative Writing Tools
7.2.2 Creative Information Retrieval of Figurative Possibilities
7.2.3 Narrative Possibilities: From Metaphor to Metamorphosis