Vector Semantics

Description

This open access book introduces Vector semantics, which links the formal theory of word vectors to the cognitive theory of linguistics.  The computational linguists and deep learning researchers who developed word vectors have relied primarily on the ever-increasing availability of large corpora and of computers with highly parallel GPU and TPU compute engines, and their focus is with endowing computers with natural language capabilities for practical applications such as machine translation or question answering. Cognitive linguists investigate natural language from the perspective of human cognition, the relation between language and thought, and questions about conceptual universals, relying primarily on in-depth investigation of language in use.  In spite of the fact that these two schools both have ‘linguistics’ in their name, so far there has been very limited communication between them, as their historical origins, data collection methods, and conceptual apparatuses are quite different. Vector semantics bridges the gap by presenting a formal theory, cast in terms of linear polytopes, that generalizes both word vectors and conceptual structures, by treating each dictionary definition as an equation, and the entire lexicon as a set of equations mutually constraining all meanings.  Preface Contents Foundations of non-compositionality Background Lexicographic principles The syntax of definitions The geometry of definitions The algebra of definitions Parallel description From morphology to syntax Lexical categories and subcategories Bound morphemes Relations Linking Naive grammar Time and space Space Time Indexicals, coercion Measure Negation Background Negation in the lexicon Negation in compositional constructions Double negation Quantifiers Disjunction Valuations and learnability The likeliness scale Naive inference (likeliness update) Learning Modality Tense and aspect The deontic world Knowledge, belief, emotions Defaults Adjectives, gradience, implicature Adjectives Gradience Implicature Spreading activation Trainability and real-world knowledge Proper names Trainability Dynamic embeddings Applications Fitting to the law Pragmatic inferencing Representation building Explainability Summary References Index External index Appendix: 4lang