Examples of SemEvalContextExtractor

edu.ucla.sspace.wordsi.semeval.SemEvalContextExtractor
A {@link ContextExtractor} for handling SemEval or SenseEval corpora. Foreach document, there should be an instance identifier, which uniquely identifies the context. There should also be some marker, i.e., "|||", that marks where the focus word is in the document. Only one context vector will be generated for each document. This class depends on a {@link ContextGenerator} for generating the context vectors. @author Keith Stevens

Examples of edu.ucla.sspace.wordsi.semeval.SemEvalContextExtractor

            SerializableUtil.load(new File(args[2]));
        basis.setReadOnly(true);
        ContextGenerator generator =
            new WordOccrrenceContextGenerator(basis, new LinearWeighting(), 25);
        ContextExtractor extractor =
            new SemEvalContextExtractor(generator, 25);


        System.out.println("Processing contexts");
        CorpusReader<Document> reader = new SemEvalLexSubReader();
        Iterator<Document> docIter = reader.read(new File(args[1]));
        while (docIter.hasNext())
            extractor.processDocument(docIter.next().reader(), wordsi);
    }

View Full Code Here

Examples of edu.ucla.sspace.wordsi.semeval.SemEvalContextExtractor

            generator.setReadOnly(true);


        // If the evaluation type is for semEval, use a
        // SemEvalContextExtractor.
        if (argOptions.hasOption('E'))
            return new SemEvalContextExtractor(
                    generator, windowSize(), argOptions.getStringOption('E'));


        // If the evaluation type is for pseudoWord, use a
        // PseudoWordContextExtractor.
        if (argOptions.hasOption('P'))

View Full Code Here

TOP

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.