Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore an in-depth analysis of a research paper proposing an innovative method to construct knowledge graphs from pre-trained language models without human supervision. Delve into the process of transforming corpus data into structured knowledge graphs, understand the candidate fact-finding algorithm, and examine the challenges of causal attention confusion. Learn about mapping facts to schemas, view examples of constructed knowledge graphs, and analyze experimental results. Gain insights into newly discovered facts and the potential implications of this approach for automated knowledge graph construction in artificial intelligence and natural language processing.
Syllabus
- Intro & Overview
- TabNine Promotion
- Title Misnomer
- From Corpus To Knowledge Graph
- Paper Contributions
- Candidate Fact Finding Algorithm
- Causal Attention Confusion
- More Constraints
- Mapping Facts To Schemas
- Example Constructed Knowledge Graph
- Experimental Results
- Example Discovered Facts
- Conclusion & My Comments
Taught by
Yannic Kilcher