Spaces:
Sleeping
Sleeping
File size: 9,676 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 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 |
"""
Tests for common methods of IBM translation models
"""
import unittest
from collections import defaultdict
from nltk.translate import AlignedSent, IBMModel
from nltk.translate.ibm_model import AlignmentInfo
class TestIBMModel(unittest.TestCase):
__TEST_SRC_SENTENCE = ["j'", "aime", "bien", "jambon"]
__TEST_TRG_SENTENCE = ["i", "love", "ham"]
def test_vocabularies_are_initialized(self):
parallel_corpora = [
AlignedSent(["one", "two", "three", "four"], ["un", "deux", "trois"]),
AlignedSent(["five", "one", "six"], ["quatre", "cinq", "six"]),
AlignedSent([], ["sept"]),
]
ibm_model = IBMModel(parallel_corpora)
self.assertEqual(len(ibm_model.src_vocab), 8)
self.assertEqual(len(ibm_model.trg_vocab), 6)
def test_vocabularies_are_initialized_even_with_empty_corpora(self):
parallel_corpora = []
ibm_model = IBMModel(parallel_corpora)
self.assertEqual(len(ibm_model.src_vocab), 1) # addition of NULL token
self.assertEqual(len(ibm_model.trg_vocab), 0)
def test_best_model2_alignment(self):
# arrange
sentence_pair = AlignedSent(
TestIBMModel.__TEST_TRG_SENTENCE, TestIBMModel.__TEST_SRC_SENTENCE
)
# None and 'bien' have zero fertility
translation_table = {
"i": {"j'": 0.9, "aime": 0.05, "bien": 0.02, "jambon": 0.03, None: 0},
"love": {"j'": 0.05, "aime": 0.9, "bien": 0.01, "jambon": 0.01, None: 0.03},
"ham": {"j'": 0, "aime": 0.01, "bien": 0, "jambon": 0.99, None: 0},
}
alignment_table = defaultdict(
lambda: defaultdict(lambda: defaultdict(lambda: defaultdict(lambda: 0.2)))
)
ibm_model = IBMModel([])
ibm_model.translation_table = translation_table
ibm_model.alignment_table = alignment_table
# act
a_info = ibm_model.best_model2_alignment(sentence_pair)
# assert
self.assertEqual(a_info.alignment[1:], (1, 2, 4)) # 0th element unused
self.assertEqual(a_info.cepts, [[], [1], [2], [], [3]])
def test_best_model2_alignment_does_not_change_pegged_alignment(self):
# arrange
sentence_pair = AlignedSent(
TestIBMModel.__TEST_TRG_SENTENCE, TestIBMModel.__TEST_SRC_SENTENCE
)
translation_table = {
"i": {"j'": 0.9, "aime": 0.05, "bien": 0.02, "jambon": 0.03, None: 0},
"love": {"j'": 0.05, "aime": 0.9, "bien": 0.01, "jambon": 0.01, None: 0.03},
"ham": {"j'": 0, "aime": 0.01, "bien": 0, "jambon": 0.99, None: 0},
}
alignment_table = defaultdict(
lambda: defaultdict(lambda: defaultdict(lambda: defaultdict(lambda: 0.2)))
)
ibm_model = IBMModel([])
ibm_model.translation_table = translation_table
ibm_model.alignment_table = alignment_table
# act: force 'love' to be pegged to 'jambon'
a_info = ibm_model.best_model2_alignment(sentence_pair, 2, 4)
# assert
self.assertEqual(a_info.alignment[1:], (1, 4, 4))
self.assertEqual(a_info.cepts, [[], [1], [], [], [2, 3]])
def test_best_model2_alignment_handles_fertile_words(self):
# arrange
sentence_pair = AlignedSent(
["i", "really", ",", "really", "love", "ham"],
TestIBMModel.__TEST_SRC_SENTENCE,
)
# 'bien' produces 2 target words: 'really' and another 'really'
translation_table = {
"i": {"j'": 0.9, "aime": 0.05, "bien": 0.02, "jambon": 0.03, None: 0},
"really": {"j'": 0, "aime": 0, "bien": 0.9, "jambon": 0.01, None: 0.09},
",": {"j'": 0, "aime": 0, "bien": 0.3, "jambon": 0, None: 0.7},
"love": {"j'": 0.05, "aime": 0.9, "bien": 0.01, "jambon": 0.01, None: 0.03},
"ham": {"j'": 0, "aime": 0.01, "bien": 0, "jambon": 0.99, None: 0},
}
alignment_table = defaultdict(
lambda: defaultdict(lambda: defaultdict(lambda: defaultdict(lambda: 0.2)))
)
ibm_model = IBMModel([])
ibm_model.translation_table = translation_table
ibm_model.alignment_table = alignment_table
# act
a_info = ibm_model.best_model2_alignment(sentence_pair)
# assert
self.assertEqual(a_info.alignment[1:], (1, 3, 0, 3, 2, 4))
self.assertEqual(a_info.cepts, [[3], [1], [5], [2, 4], [6]])
def test_best_model2_alignment_handles_empty_src_sentence(self):
# arrange
sentence_pair = AlignedSent(TestIBMModel.__TEST_TRG_SENTENCE, [])
ibm_model = IBMModel([])
# act
a_info = ibm_model.best_model2_alignment(sentence_pair)
# assert
self.assertEqual(a_info.alignment[1:], (0, 0, 0))
self.assertEqual(a_info.cepts, [[1, 2, 3]])
def test_best_model2_alignment_handles_empty_trg_sentence(self):
# arrange
sentence_pair = AlignedSent([], TestIBMModel.__TEST_SRC_SENTENCE)
ibm_model = IBMModel([])
# act
a_info = ibm_model.best_model2_alignment(sentence_pair)
# assert
self.assertEqual(a_info.alignment[1:], ())
self.assertEqual(a_info.cepts, [[], [], [], [], []])
def test_neighboring_finds_neighbor_alignments(self):
# arrange
a_info = AlignmentInfo(
(0, 3, 2),
(None, "des", "œufs", "verts"),
("UNUSED", "green", "eggs"),
[[], [], [2], [1]],
)
ibm_model = IBMModel([])
# act
neighbors = ibm_model.neighboring(a_info)
# assert
neighbor_alignments = set()
for neighbor in neighbors:
neighbor_alignments.add(neighbor.alignment)
expected_alignments = {
# moves
(0, 0, 2),
(0, 1, 2),
(0, 2, 2),
(0, 3, 0),
(0, 3, 1),
(0, 3, 3),
# swaps
(0, 2, 3),
# original alignment
(0, 3, 2),
}
self.assertEqual(neighbor_alignments, expected_alignments)
def test_neighboring_sets_neighbor_alignment_info(self):
# arrange
a_info = AlignmentInfo(
(0, 3, 2),
(None, "des", "œufs", "verts"),
("UNUSED", "green", "eggs"),
[[], [], [2], [1]],
)
ibm_model = IBMModel([])
# act
neighbors = ibm_model.neighboring(a_info)
# assert: select a few particular alignments
for neighbor in neighbors:
if neighbor.alignment == (0, 2, 2):
moved_alignment = neighbor
elif neighbor.alignment == (0, 3, 2):
swapped_alignment = neighbor
self.assertEqual(moved_alignment.cepts, [[], [], [1, 2], []])
self.assertEqual(swapped_alignment.cepts, [[], [], [2], [1]])
def test_neighboring_returns_neighbors_with_pegged_alignment(self):
# arrange
a_info = AlignmentInfo(
(0, 3, 2),
(None, "des", "œufs", "verts"),
("UNUSED", "green", "eggs"),
[[], [], [2], [1]],
)
ibm_model = IBMModel([])
# act: peg 'eggs' to align with 'œufs'
neighbors = ibm_model.neighboring(a_info, 2)
# assert
neighbor_alignments = set()
for neighbor in neighbors:
neighbor_alignments.add(neighbor.alignment)
expected_alignments = {
# moves
(0, 0, 2),
(0, 1, 2),
(0, 2, 2),
# no swaps
# original alignment
(0, 3, 2),
}
self.assertEqual(neighbor_alignments, expected_alignments)
def test_hillclimb(self):
# arrange
initial_alignment = AlignmentInfo((0, 3, 2), None, None, None)
def neighboring_mock(a, j):
if a.alignment == (0, 3, 2):
return {
AlignmentInfo((0, 2, 2), None, None, None),
AlignmentInfo((0, 1, 1), None, None, None),
}
elif a.alignment == (0, 2, 2):
return {
AlignmentInfo((0, 3, 3), None, None, None),
AlignmentInfo((0, 4, 4), None, None, None),
}
return set()
def prob_t_a_given_s_mock(a):
prob_values = {
(0, 3, 2): 0.5,
(0, 2, 2): 0.6,
(0, 1, 1): 0.4,
(0, 3, 3): 0.6,
(0, 4, 4): 0.7,
}
return prob_values.get(a.alignment, 0.01)
ibm_model = IBMModel([])
ibm_model.neighboring = neighboring_mock
ibm_model.prob_t_a_given_s = prob_t_a_given_s_mock
# act
best_alignment = ibm_model.hillclimb(initial_alignment)
# assert: hill climbing goes from (0, 3, 2) -> (0, 2, 2) -> (0, 4, 4)
self.assertEqual(best_alignment.alignment, (0, 4, 4))
def test_sample(self):
# arrange
sentence_pair = AlignedSent(
TestIBMModel.__TEST_TRG_SENTENCE, TestIBMModel.__TEST_SRC_SENTENCE
)
ibm_model = IBMModel([])
ibm_model.prob_t_a_given_s = lambda x: 0.001
# act
samples, best_alignment = ibm_model.sample(sentence_pair)
# assert
self.assertEqual(len(samples), 61)
|