Language Generation in the Limit - Transformers as a Computational Model
Offered By: Simons Institute via YouTube
Course Description
Overview
Explore language generation fundamentals in this 52-minute lecture by Jon Kleinberg from Cornell University. Delve into the core specifications of language generation problems, examining how to produce valid new strings from an unknown language using only finite training samples. Investigate models where an adversary enumerates strings from an unknown target language, and discover the non-trivial guarantees possible in this setting. Compare these findings with Gold and Angluin's negative results in language learning, highlighting the fundamental differences between language identification and generation. Gain insights into Transformers as a computational model and the implications for current large language models.
Syllabus
Language Generation in the Limit
Taught by
Simons Institute
Related Courses
Logic: Language and Information 1University of Melbourne via Coursera Logic: Language and Information 2
University of Melbourne via Coursera Language, Proof and Logic
Stanford University via edX 理论计算机科学基础 | Introduction to Theoretical Computer Science
Peking University via edX 离散数学概论 Discrete Mathematics Generality
Peking University via Coursera