3252f2117a4b693ca001613b13c28cc2d8cd9eb7,tests/candidates/test_candidates.py,,test_ngrams,#,424

Before Change

    corpus_parser.apply(doc_preprocessor, parallelism=PARALLEL)
    assert session.query(Document).count() == max_docs
    assert session.query(Sentence).count() == 503
    docs = session.query(Document).order_by(Document.name).all()

    // Mention Extraction
    Person = mention_subclass("Person")
    person_ngrams = MentionNgrams(n_max=3)

After Change

    assert len([x for x in mentions if x.context.get_num_words() > 3]) == 0

    // Test for unigram exclusion
    for mention in doc.persons[:]:
        doc.persons.remove(mention)
    assert len(doc.persons) == 0

    person_ngrams = MentionNgrams(n_min=2, n_max=3)
    mention_extractor_udf = MentionExtractorUDF(

Instances