Sumários

Document classification and clustering

18 outubro 2018, 15:30 João Miguel Cordeiro Monteiro

  • Document classification/clustering with the Python scikit-learn library
  • Implementing naive Bayes and K-nearest neighbour classifiers
  • Pen-and-paper exercises about document classification with the Naive Bayes and the Perceptron algorithms
  • Pen-and-paper exercise about document clustering with the K-means algorithm


Information Extraction

18 outubro 2018, 14:00 Pável Pereira Calado

  • Introduction to Information Extraction
  • Information Extraction Tasks (e.g., entity and relation extraction) and Applications (e.g., open-domain IE)
  • Rule-based versus Machine Learning Methods for Information Extraction
  • Usage of Regular Expressions in Rule-based Methods
  • Modeling Information Extraction as a Sequence Classification Problem
  • Introduction to Hidden Markov Models


Document classification and clustering

17 outubro 2018, 11:30 João Miguel Cordeiro Monteiro

  • Document classification/clustering with the Python scikit-learn library
  • Implementing naive Bayes and K-nearest neighbour classifiers
  • Pen-and-paper exercises about document classification with the Naive Bayes and the Perceptron algorithms
  • Pen-and-paper exercise about document clustering with the K-means algorithm


Information Extraction

15 outubro 2018, 17:00 Bruno Emanuel Da Graça Martins

  • Introduction to Information Extraction
    • IE Problems and Tasks
    • Overview on Techniques for IE
    • Encoding Named Entity Recognition as Sequence Labeling
  • Information Extraction with Hidden Markov Models
    • Introduction to Hidden Markov Models
    • Inferring the Probability of an Observation Sequence (Forward Algorithm)


Clustering and Dimensionality Reduction

12 outubro 2018, 14:00 Pável Pereira Calado

  • The Clustering Hypothesis in Information Retrieval
  • Applications of Clustering and Dimensionality Reduction in Information Retrieval
  • Clustering Techniques
    • Hierarchical Agglomerative Clustering
    • K-Means and Soft K-Means
  • Dimensionality Reduction Techniques
    • Self-Organising Maps
    • Multidimensional Scaling
    • Latent Semantic Indexing