Exemple #1
0
 def __init__(self, text_or_tokens, max_sentence_length=399):
     if isinstance(text_or_tokens, Sentence):
         self.sentrep = text_or_tokens.sentrep
     elif isinstance(text_or_tokens, basestring):
         self.sentrep = parser.tokenize('<s> ' + text_or_tokens + ' </s>',
                                        max_sentence_length)
     else:
         self.sentrep = parser.SentRep(text_or_tokens)
def test_parse():
    sr1 = parser.SentRep(['These', 'are', 'tokens', '.'])
    sr2 = test_tokenizer()

    for sr in (sr1, sr2):
        parses = parser.parse(sr, thread_slot)
        display_parses(parses)
        print '---'
def test_extpos():
    sr1 = parser.SentRep(['record'])

    print 'Unconstrained'
    display_parses(parser.parse(sr1, thread_slot))

    print 'NN'
    ext_pos1 = parser.ExtPos()
    ext_pos1.addTagConstraints(parser.VectorString(['NN']))

    display_parses(parser.parse(sr1, ext_pos1, thread_slot))

    print 'VB'
    ext_pos2 = parser.ExtPos()
    ext_pos2.addTagConstraints(parser.VectorString(['VB']))
    display_parses(parser.parse(sr1, ext_pos2, thread_slot))
def test_multiword_extpos():
    sr1 = parser.SentRep('British left waffles on Falklands .'.split())

    print 'waffles = [anything]:'
    display_parses(parser.parse(sr1, thread_slot))

    if 1:
        print 'waffles = VBZ/VBD/VB:'
        ext_pos = parser.ExtPos()
        ext_pos.addTagConstraints(parser.VectorString([]))
        ext_pos.addTagConstraints(parser.VectorString([]))
        ext_pos.addTagConstraints(parser.VectorString(['VBZ', 'VBD', 'VB']))
        ext_pos.addTagConstraints(parser.VectorString([]))
        ext_pos.addTagConstraints(parser.VectorString([]))
        ext_pos.addTagConstraints(parser.VectorString([]))
        display_parses(parser.parse(sr1, ext_pos, thread_slot))

        print 'waffles = NNS:'
        ext_pos = parser.ExtPos()
        ext_pos.addTagConstraints(parser.VectorString([]))
        ext_pos.addTagConstraints(parser.VectorString([]))
        ext_pos.addTagConstraints(parser.VectorString(['NNS']))
        ext_pos.addTagConstraints(parser.VectorString([]))
        ext_pos.addTagConstraints(parser.VectorString([]))
        ext_pos.addTagConstraints(parser.VectorString([]))
        display_parses(parser.parse(sr1, ext_pos, thread_slot))

        print 'waffles = NN/NNS:'
        ext_pos = parser.ExtPos()
        ext_pos.addTagConstraints(parser.VectorString([]))
        ext_pos.addTagConstraints(parser.VectorString([]))
        ext_pos.addTagConstraints(parser.VectorString(['NN', 'NNS']))
        ext_pos.addTagConstraints(parser.VectorString([]))
        ext_pos.addTagConstraints(parser.VectorString([]))
        ext_pos.addTagConstraints(parser.VectorString([]))
        display_parses(parser.parse(sr1, ext_pos, thread_slot))
def test_as_nbest_list():
    sr1 = parser.SentRep(['These', 'are', 'tokens', '.'])
    parses = parser.parse(sr1, thread_slot)
    print parser.asNBestList(parses)
Exemple #6
0
def test_as_nbest_list():
    sr1 = parser.SentRep(['These', 'are', 'tokens', '.'])
    parses = parser.parse(sr1)
    print parser.asNBestList(parses, 'test_as_nbest_list_sentence')