Web Crawling (cont.)

15 novembro 2019, 12:30 • Bruno Emanuel Da Graça Martins

• Universal crawlers
  
• Concurrent crawlers
• Freshness by prioritising according to predictions for changed contents
• Coverage by prioritising according to PageRank
• Preferential crawlers
• Bias of Breadth-first Crawlers
• Focused crawlers leveraging supervised learning
• Topical crawlers leveraging similarity towards topic
• Adaptive crawlers
• Figures of merit for preferential crawlers
• Crawler etiquette
• Crawler ethics and conflicts
• The robots exclusion protocol
• Introduction to min-hash and high-dimensional similarity search

Web Crawling (cont.)

15 novembro 2019, 12:30 • Bruno Emanuel Da Graça Martins

• Universal crawlers
  
• Concurrent crawlers
• Freshness by prioritising according to predictions for changed contents
• Coverage by prioritising according to PageRank
• Preferential crawlers
• Bias of Breadth-first Crawlers
• Focused crawlers leveraging supervised learning
• Topical crawlers leveraging similarity towards topic
• Adaptive crawlers
• Figures of merit for preferential crawlers
• Crawler etiquette
• Crawler ethics and conflicts
• The robots exclusion protocol
• Introduction to min-hash and high-dimensional similarity search

Lab 05 - Part 2: Information Extraction

15 novembro 2019, 11:00 • Danielle Caled Vieira

Hidden Markov Models

• Pen and paper exercises using structured perceptron

Lab 05 - Part 2: Information Extraction

15 novembro 2019, 09:30 • Danielle Caled Vieira

Hidden Markov Models

• Pen and paper exercises using structured perceptron

Learning to Rank

14 novembro 2019, 17:00 • João Miguel Cordeiro Monteiro

• Python exercises on Learning to Rank
• Pointwise L2R approaches using Logistic Regression
  
• Pen and paper exercise using the perceptron ranking algorithm