Low-Pass Semantics with a Bit of Discourse - November 2013
Center for Language & Speech Processing(CLSP), JHU via YouTube
Master Windows Internals - Kernel Programming, Debugging & Architecture
Lead AI Strategy with UCSB's Agentic AI Program — Microsoft Certified
Overview
Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
Explore a comprehensive lecture on the challenges and future directions of natural language processing, delivered by Fernando Pereira, research director at Google. Delve into the advancements in statistical and machine learning approaches to language analysis, and understand their applications in information retrieval, speech recognition, and machine translation. Examine the limitations of current language processing systems and the need for deeper linguistic analysis to create more robust and accurate methods. Learn about the concept of "low-pass semantics" and how it leverages distributional regularities and redundancy in large text collections to improve language understanding. Gain insights into the main language processing challenges of the coming decade, including the creation of systems that can understand entities, concepts, and claims in text. Discover how this knowledge can be applied to enhance question answering, knowledge base updating, and argument tracing in written records.
Syllabus
Low-Pass Semantics (with a Bit of Discourse) - Fernando Pereira (Google) - Nov 2013
Taught by
Center for Language & Speech Processing(CLSP), JHU