Overview
- This book is open access, which means that you have free and unlimited access
- Links the formal theory of word vectors to the cognitive theory of linguistics
- Unifies theories originating in linguistics, logic, artificial intelligence, cognitive science, etc
- Provides rich inline references to allow broader readership to understand the book content
Part of the book series: Cognitive Technologies (COGTECH)
Buy print copy
Tax calculation will be finalised at checkout
About this book
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.
Similar content being viewed by others
Keywords
Table of contents (9 chapters)
Authors and Affiliations
About the author
Kornai has broad experience in industrial research (Xerox, IBM, BBN) and at startups (MAD, Calera, Belmont, Northern Light, MetaCarta, MindSpeak) working as chief scientist at the last three. Several of these startups were purchased by industry leaders (Nuance, PPD, Microsoft) and muchof the technology developed under his leadership is still in use. He held various visiting and research positions at Rice University, Boston University, and Harvard. He currently leads the SZTAKI/BME Human Language Technology group.
MindSpeak), working as chief scientist at the last three. Several of these startups were purchased by industry leaders (Nuance, PPD, Microsoft) and much of the technology developed under his leadership is still in use. He held various visiting and research positions at Rice University, Boston University, and Harvard. He currently leads the SZTAKI/BME Human Language Technology group.MindSpeak), working as chief scientist at the last three. Several of these startups were purchased by industry leaders (Nuance, PPD, Microsoft) and much of the technology developed under his leadership is still in use. He held various visiting and research positions at Rice University, Boston University, and Harvard. He currently leads the SZTAKI/BME Human Language Technology group. MindSpeak), working as chief scientist at the last three. Several of these startups were purchased by industry leaders (Nuance, PPD, Microsoft) and much of the technology developed under his leadership is still in use. He held various visiting and research positions at Rice University, Boston University, and Harvard. He currently leads the SZTAKI/BME Human Language Technology groupBibliographic Information
Book Title: Vector Semantics
Authors: András Kornai
Series Title: Cognitive Technologies
DOI: https://doi.org/10.1007/978-981-19-5607-2
Publisher: Springer Singapore
eBook Packages: Computer Science, Computer Science (R0)
Copyright Information: The Author(s) 2023
Hardcover ISBN: 978-981-19-5606-5Published: 07 December 2022
Softcover ISBN: 978-981-19-5609-6Published: 07 December 2022
eBook ISBN: 978-981-19-5607-2Published: 06 December 2022
Series ISSN: 1611-2482
Series E-ISSN: 2197-6635
Edition Number: 1
Number of Pages: XVI, 273
Topics: Natural Language Processing (NLP), Computational Linguistics, Artificial Intelligence, Machine Learning, Knowledge based Systems, Digital Humanities