Machine Learning in GATE

1
Machine Learning in GATE

• Valentin Tablan

2
Machine Learning in GATE

• Uses classification.
• Attr1, Attr2, Attr3, Attrn ? Class
• Classifies annotations.
• (Documents can be classified as well using a
  simple trick.)
• Annotations of a particular type are selected as
  instances.
• Attributes refer to instance annotations.
• Attributes have a position relative to the
  instance annotation they refer to.

3
Attributes

• Attributes can be
• Boolean
• The lack of presence of an annotation of a
  particular type partially overlapping the
  referred instance annotation.
• Nominal
• The value of a particular feature of the referred
  instance annotation. The complete set of
  acceptable values must be specified a-priori.
• Numeric
• The numeric value (converted from String) of a
  particular feature of the referred instance
  annotation.

4
Implementation

• Machine Learning PR in GATE.
• Has two functioning modes
• training
• application
• Uses an XML file for configuration
• lt?xml version"1.0" encoding"windows-1252"?gt
• ltML-CONFIGgt
• ltDATASETgt lt/DATASETgt
• ltENGINEgtlt/ENGINEgt
• ltML-CONFIGgt

5
ltDATASETgt

• ltDATASETgt
• ltINSTANCE-TYPEgtTokenlt/INSTANCE-TYPEgt
• ltATTRIBUTEgt
• ltNAMEgtPOS_category(0)lt/NAMEgt
• ltTYPEgtTokenlt/TYPEgt
• ltFEATUREgtcategorylt/FEATUREgt
• ltPOSITIONgt0lt/POSITIONgt
• ltVALUESgt
• ltVALUEgtNNlt/VALUEgt
• ltVALUEgtNNPlt/VALUEgt
• ltVALUEgtNNPSlt/VALUEgt
• lt/VALUESgt
• ltCLASS/gt
• lt/ATTRIBUTEgt
• lt/DATASETgt

6
ltENGINEgt

• ltENGINEgt
• ltWRAPPERgtgate.creole.ml.weka.Wrapperlt/WRAPPERgt
  
• ltOPTIONSgt
• ltCLASSIFIERgtweka.classifiers.j48.J48lt/CLASS
  IFIERgt
• ltCLASSIFIER-OPTIONSgt-K 3lt/CLASSIFIER-OPTION
  Sgt
• ltCONFIDENCE-THRESHOLDgt0.85lt/CONFIDENCE-THRE
  SHOLDgt
• lt/OPTIONSgt
• lt/ENGINEgt

7
Attributes Position
Instances type Token
8
Machine Learning PR

• Can save a learnt model to an external file for
  later use.
• Saves the actual model and the collected dataset.
• Can export the collected dataset in .arff format.

9
Standard Use Scenario

• Application
• Prepare data by enriching the documents with
  annotation for attributes. (e.g. run Tokeniser,
  POS tagger, Gazetteer, etc).
• Load the previously saved model.
• Run the ML PR in application mode.
• Save the learnt model.

• Training
• Prepare training data by enriching the documents
  with annotation for attributes. (e.g. run
  Tokeniser, POS tagger, Gazetteer, etc).
• Run the ML PR in training mode.
• Export the dataset as .arff and perform
  experiments using the WEKA interface in order to
  find the best attribute set / algorithm /
  algorithm options.
• Update the configuration file accordingly.
• Run the ML PR again to collect the actual data.
• Save the learnt model.

10
An Example

• Learn POS category from POS context.

11
Using Other ML Libraries

• The MLEngine Interface
• Method Summary
• void addTrainingInstance(List attributes) Adds
  a new training instance to the dataset. 
• Object classifyInstance(List attributes)
  Classifies a new instance. 
• void init() This method will be called after an
  engine is created and has its dataset and options
  set. 
• void setDatasetDefinition(DatasetDefintion definit
  ion) Sets the definition for the dataset used. 
• void setOptions(org.jdom.Element options) Sets
  the options from an XML JDom element.
• void setOwnerPR(ProcessingResource pr)
  Registers the PR using the engine with the
  engine.