Spaces:
Sleeping
Sleeping
File size: 5,204 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 |
from nltk.translate.ribes_score import corpus_ribes, word_rank_alignment
def test_ribes_empty_worder(): # worder as in word order
# Verifies that these two sentences have no alignment,
# and hence have the lowest possible RIBES score.
hyp = "This is a nice sentence which I quite like".split()
ref = "Okay well that's neat and all but the reference's different".split()
assert word_rank_alignment(ref, hyp) == []
list_of_refs = [[ref]]
hypotheses = [hyp]
assert corpus_ribes(list_of_refs, hypotheses) == 0.0
def test_ribes_one_worder():
# Verifies that these two sentences have just one match,
# and the RIBES score for this sentence with very little
# correspondence is 0.
hyp = "This is a nice sentence which I quite like".split()
ref = "Okay well that's nice and all but the reference's different".split()
assert word_rank_alignment(ref, hyp) == [3]
list_of_refs = [[ref]]
hypotheses = [hyp]
assert corpus_ribes(list_of_refs, hypotheses) == 0.0
def test_ribes_two_worder():
# Verifies that these two sentences have two matches,
# but still get the lowest possible RIBES score due
# to the lack of similarity.
hyp = "This is a nice sentence which I quite like".split()
ref = "Okay well that's nice and all but the reference is different".split()
assert word_rank_alignment(ref, hyp) == [9, 3]
list_of_refs = [[ref]]
hypotheses = [hyp]
assert corpus_ribes(list_of_refs, hypotheses) == 0.0
def test_ribes():
# Based on the doctest of the corpus_ribes function
hyp1 = [
"It",
"is",
"a",
"guide",
"to",
"action",
"which",
"ensures",
"that",
"the",
"military",
"always",
"obeys",
"the",
"commands",
"of",
"the",
"party",
]
ref1a = [
"It",
"is",
"a",
"guide",
"to",
"action",
"that",
"ensures",
"that",
"the",
"military",
"will",
"forever",
"heed",
"Party",
"commands",
]
ref1b = [
"It",
"is",
"the",
"guiding",
"principle",
"which",
"guarantees",
"the",
"military",
"forces",
"always",
"being",
"under",
"the",
"command",
"of",
"the",
"Party",
]
ref1c = [
"It",
"is",
"the",
"practical",
"guide",
"for",
"the",
"army",
"always",
"to",
"heed",
"the",
"directions",
"of",
"the",
"party",
]
hyp2 = [
"he",
"read",
"the",
"book",
"because",
"he",
"was",
"interested",
"in",
"world",
"history",
]
ref2a = [
"he",
"was",
"interested",
"in",
"world",
"history",
"because",
"he",
"read",
"the",
"book",
]
list_of_refs = [[ref1a, ref1b, ref1c], [ref2a]]
hypotheses = [hyp1, hyp2]
score = corpus_ribes(list_of_refs, hypotheses)
assert round(score, 4) == 0.3597
def test_no_zero_div():
# Regression test for Issue 2529, assure that no ZeroDivisionError is thrown.
hyp1 = [
"It",
"is",
"a",
"guide",
"to",
"action",
"which",
"ensures",
"that",
"the",
"military",
"always",
"obeys",
"the",
"commands",
"of",
"the",
"party",
]
ref1a = [
"It",
"is",
"a",
"guide",
"to",
"action",
"that",
"ensures",
"that",
"the",
"military",
"will",
"forever",
"heed",
"Party",
"commands",
]
ref1b = [
"It",
"is",
"the",
"guiding",
"principle",
"which",
"guarantees",
"the",
"military",
"forces",
"always",
"being",
"under",
"the",
"command",
"of",
"the",
"Party",
]
ref1c = [
"It",
"is",
"the",
"practical",
"guide",
"for",
"the",
"army",
"always",
"to",
"heed",
"the",
"directions",
"of",
"the",
"party",
]
hyp2 = ["he", "read", "the"]
ref2a = ["he", "was", "interested", "in", "world", "history", "because", "he"]
list_of_refs = [[ref1a, ref1b, ref1c], [ref2a]]
hypotheses = [hyp1, hyp2]
score = corpus_ribes(list_of_refs, hypotheses)
assert round(score, 4) == 0.1688
|