CMU Advanced NLP: Experimental Design
Offered By: Graham Neubig via YouTube
Course Description
Overview
Explore experimental design in advanced natural language processing through this comprehensive lecture. Learn about the scientific method, formulating research questions, conducting literature surveys, and developing hypotheses. Discover techniques for running experiments, including data collection, annotation guidelines, and statistical significance testing. Gain insights into identifying promising research directions, from curiosity-driven approaches to application-focused inquiries. Understand the importance of proper experimental setup and evaluation metrics in NLP research. Access valuable resources for finding relevant papers and datasets to support your investigations.
Syllabus
Intro
Identify good research directions
Examples of applications
Curiosity driven research
Bottomup discovery
Research survey methods
Where to find papers
ACL Anthology
Google Scholar
Resources
Research Question
Hypothesis
Application Driven Questions
Testing with Experiments
Obtaining Test Data
Finding Datasets
Annotation
Statistical significance testing
Sample data
Annotation guidelines
Annotation methods
Measure metrics
Taught by
Graham Neubig
Related Courses
Natural Language ProcessingColumbia University via Coursera Natural Language Processing
Stanford University via Coursera Introduction to Natural Language Processing
University of Michigan via Coursera moocTLH: Nuevos retos en las tecnologĂas del lenguaje humano
Universidad de Alicante via MirĂadax Natural Language Processing
Indian Institute of Technology, Kharagpur via Swayam