Skip to end of metadata
Go to start of metadata
Title No. of slides Description
Introduction to GATE and Text Mining    
Module 1 - Introduction to GATE Developer
58
  • Finding your way around the GATE GUI
  • Loading and Viewing Documents
  • All about Annotations
  • Documents and Corpora
  • Processing Resources and Plugins
  • Applications
  • Saving documents
Module 2 - Introduction to IE and ANNIE
145
  • Introduction to IE
  • ANNIE
  • Multilingual tools in GATE
  • Evaluation and Corpus Quality Assurance
Module 3 - Introduction to JAPE
61
  • What is JAPE?
  • Parts of the rule: LHS and RHS
  • How to write simple patterns
  • How to create new annotations and features
  • Different operators
  • Different matching styles
  • Macros
Module 4 - Taking GATE to the Cloud
45





38


20
  • Part I: Teamware
    • What is it?
    • Teamware for annotation
    • Teamware for quality assurance and curation
    • Teamware for defining workflows, running automatic services, managing annotation projects
  • Part II: GATE Cloud.net
    • What is it?
    • What is it for me?
  • Part III: Mimir – Multi-paradigm indexing
    • What is it?
    • Why Mimir?
    • Searching with Mimir
    • Mimir query language
Programming in GATE    
Module 5 - GATE Embedded API
66
  • GATE API Basics
  • The CREOLE Model
  • CREOLE Basics
  • Resources, Parameters, Features
  • Annotations, Documents, Corpora
  • Execution Control
  • PR and Language Analysers
  • Controllers
Module 6 - GATE APIs
88
  • Using Java in JAPE
  • Basic JAPE
  • Java on the RHS
  • Common idioms
  • The GATE Ontology API
  • 5 minute guide to ontologies
  • Ontologies in GATE Embedded
  • Optional Material
  • Advanced JAPE
Module 7 - Creating New Resource Types
59
  • CREOLE Basics
    • CREOLE Recap
    • CREOLE Metadata
  • Creating CREOLE Resources
    • Your First Language Analyser
    • Best Practice
    • Your First Visual Resource
  • Advanced CREOLE
    • CREOLE Management Corpus-level processing
    • Adding actions to the GUI
Module 8 - Advanced GATE Embedded
108
  • GATE in Multi-threaded/Web Applications
    • Introduction
    • Multi-threading and GATE
    • Servlet Example
    • The Spring Framework
    • Making your own PRs duplication-friendly
  • GATE and Groovy
    • Introduction to Groovy
    • Scripting GATE Developer
    • Groovy Scripting for PRs and Controllers
    • Writing GATE Resource Classes in Groovy
  • Extending GATE
    • Adding new document formats
Advanced GATE    
Module 9 - Ontologies and Semantic Annotation
95
  • Brief introduction to ontologies, semantic annotation
    • URIs, Labels, Comments + Hands-on
    • Datatype Properties, Object Properties
    • Traditional NE recognition
    • Co-reference, Relations
    • Richer NE Tagging
    • Ontology-based IE
  • Manual ontology editing in GATE
  • Manual semantic annotation using OAT and RAT
  • Automatic semantic annotation using
  • OntoRoot Gazetteer and ontology-aware JAPE
  • LKB Gazetteer
  • Ontology-based evaluation using BDM
Module 10 - Advanced GATE Applications 115 This module is about adapting ANNIE to create your own applications, and to look at more advanced techniques within applications:
  • Adapting ANNIE to different languages
  • Using conditional applications
  • Section-by-section processing
  • Using multiple annotation sets
  • Separating useful content in a document
  • Schema Enforcer
  • Using Groovy
Module 11 - Machine Learning
100






61
  • Part I: ML
    • What is Machine Learning and why do we want to do it?
    • Setting up a Corpus
    • The Configuration File
    • Running the ML PR in evaluation mode
    • Evaluation in Machine Learning
    • Engines and Algorithms
  • Part II: ML Supplementary Material
    • The GATE approach to learning relations
    • How we represent relations
    • How we represent machine learning instances
    • How we represent and create features of these instances
    • Configuring the Batch Learning PR
Module 12 - Opinion Mining
109
  • Introduced the concept of Opinion Mining and Sentiment Analysis
  • Simple examples of rule-based and ML methods for creating OM applications
  • Examples of how deeper linguistic information can be useful Practice with complex applications
  • Looking ahead to the future
Labels:
None
Enter labels to add to this page:
Please wait 
Looking for a label? Just start typing.