Spaces:
Sleeping
Sleeping
File size: 2,669 Bytes
d916065 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 |
"""
Tests for IBM Model 1 training methods
"""
import unittest
from collections import defaultdict
from nltk.translate import AlignedSent, IBMModel, IBMModel1
from nltk.translate.ibm_model import AlignmentInfo
class TestIBMModel1(unittest.TestCase):
def test_set_uniform_translation_probabilities(self):
# arrange
corpus = [
AlignedSent(["ham", "eggs"], ["schinken", "schinken", "eier"]),
AlignedSent(["spam", "spam", "spam", "spam"], ["spam", "spam"]),
]
model1 = IBMModel1(corpus, 0)
# act
model1.set_uniform_probabilities(corpus)
# assert
# expected_prob = 1.0 / (target vocab size + 1)
self.assertEqual(model1.translation_table["ham"]["eier"], 1.0 / 3)
self.assertEqual(model1.translation_table["eggs"][None], 1.0 / 3)
def test_set_uniform_translation_probabilities_of_non_domain_values(self):
# arrange
corpus = [
AlignedSent(["ham", "eggs"], ["schinken", "schinken", "eier"]),
AlignedSent(["spam", "spam", "spam", "spam"], ["spam", "spam"]),
]
model1 = IBMModel1(corpus, 0)
# act
model1.set_uniform_probabilities(corpus)
# assert
# examine target words that are not in the training data domain
self.assertEqual(model1.translation_table["parrot"]["eier"], IBMModel.MIN_PROB)
def test_prob_t_a_given_s(self):
# arrange
src_sentence = ["ich", "esse", "ja", "gern", "räucherschinken"]
trg_sentence = ["i", "love", "to", "eat", "smoked", "ham"]
corpus = [AlignedSent(trg_sentence, src_sentence)]
alignment_info = AlignmentInfo(
(0, 1, 4, 0, 2, 5, 5),
[None] + src_sentence,
["UNUSED"] + trg_sentence,
None,
)
translation_table = defaultdict(lambda: defaultdict(float))
translation_table["i"]["ich"] = 0.98
translation_table["love"]["gern"] = 0.98
translation_table["to"][None] = 0.98
translation_table["eat"]["esse"] = 0.98
translation_table["smoked"]["räucherschinken"] = 0.98
translation_table["ham"]["räucherschinken"] = 0.98
model1 = IBMModel1(corpus, 0)
model1.translation_table = translation_table
# act
probability = model1.prob_t_a_given_s(alignment_info)
# assert
lexical_translation = 0.98 * 0.98 * 0.98 * 0.98 * 0.98 * 0.98
expected_probability = lexical_translation
self.assertEqual(round(probability, 4), round(expected_probability, 4))
|