/// <summary>Create a ne OpenIE system, based on the given properties.</summary>
/// <param name="props">The properties to parametrize the system with.</param>
public OpenIE(Properties props)
{
//
// TODO(gabor): handle things like "One example of chemical energy is that found in the food that we eat ."
//
//
// Static Options (for running standalone)
//
//
// Annotator Options (for running in the pipeline)
//
// Fill the properties
ArgumentParser.FillOptions(this, props);
Properties withoutOpenIEPrefix = new Properties();
foreach (string key in props.StringPropertyNames())
{
withoutOpenIEPrefix.SetProperty(key.Replace("openie.", string.Empty), props.GetProperty(key));
}
ArgumentParser.FillOptions(this, withoutOpenIEPrefix);
// Create the clause splitter
try
{
if (splitterDisable)
{
clauseSplitter = Optional.Empty();
}
else
{
if (noModel)
{
log.Info("Not loading a splitter model");
clauseSplitter = Optional.Of(null);
}
else
{
clauseSplitter = Optional.Of(IClauseSplitter.Load(splitterModel));
}
}
}
catch (IOException e)
{
//throw new RuntimeIOException("Could not load clause splitter model at " + splitterModel + ": " + e.getClass() + ": " + e.getMessage());
throw new RuntimeIOException("Could not load clause splitter model at " + splitterModel, e);
}
// Create the forward entailer
try
{
this.weights = ignoreAffinity ? new NaturalLogicWeights(affinityProbabilityCap) : new NaturalLogicWeights(affinityModels, affinityProbabilityCap);
}
catch (IOException e)
{
throw new RuntimeIOException("Could not load affinity model at " + affinityModels + ": " + e.Message);
}
forwardEntailer = new ForwardEntailer(entailmentsPerSentence, weights);
// Create the relation segmenter
segmenter = new RelationTripleSegmenter(allNominals);
}
/// <summary>The main entry point of the code.</summary>
/// <exception cref="System.IO.IOException"/>
public static void Main(string[] args)
{
Redwood.Util.ForceTrack("Processing treebanks");
IList <Pair <ICoreMap, ICollection <Pair <Span, Span> > > > trainingData = new List <Pair <ICoreMap, ICollection <Pair <Span, Span> > > >();
Sharpen.Collections.AddAll(trainingData, ProcessDirectory("WSJ", new File("/home/gabor/lib/data/penn_treebank/wsj")));
Sharpen.Collections.AddAll(trainingData, ProcessDirectory("Brown", new File("/home/gabor/lib/data/penn_treebank/brown")));
Redwood.Util.EndTrack("Processing treebanks");
Redwood.Util.ForceTrack("Training");
Redwood.Util.Log("dataset size: " + trainingData.Count);
IClauseSplitter.Train(trainingData.Stream(), new File("/home/gabor/tmp/clauseSearcher.ser.gz"), new File("/home/gabor/tmp/clauseSearcherData.tab.gz"));
Redwood.Util.EndTrack("Training");
}
