-
Notifications
You must be signed in to change notification settings - Fork 3k
/
Copy pathtest_text_similarity.py
183 lines (165 loc) · 7.7 KB
/
test_text_similarity.py
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
# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import unittest
from tempfile import TemporaryDirectory
from paddlenlp.taskflow import Taskflow
from paddlenlp.taskflow.text_similarity import TextSimilarityTask
class TestTextSimilarityTask(unittest.TestCase):
@classmethod
def setUpClass(cls):
cls.temp_dir = TemporaryDirectory()
cls.max_seq_len = 32
cls.model = "__internal_testing__/tiny-random-rocketqa-cross-encoder"
@classmethod
def tearDownClass(cls):
cls.temp_dir.cleanup()
def test_bert_model(self):
# static simbert test
similarity = Taskflow(
task="text_similarity",
model="__internal_testing__/tiny-random-bert",
)
results = similarity([["世界上什么东西最小", "世界上什么东西最小？"]])
self.assertTrue(len(results) == 1)
self.assertTrue("text1" in results[0])
self.assertTrue("text2" in results[0])
self.assertIsInstance(results[0]["similarity"], float)
results = similarity([["光眼睛大就好看吗", "眼睛好看吗？"], ["小蝌蚪找妈妈怎么样", "小蝌蚪找妈妈是谁画的"]])
self.assertTrue(len(results) == 2)
for result in results:
self.assertTrue("text1" in result)
self.assertTrue("text2" in result)
self.assertIsInstance(result["similarity"], float)
def test_text_similarity_task(self):
# static rocketqa test
input_text = ([["世界上什么东西最小", "世界上什么东西最小？"]],)
static_taskflow = TextSimilarityTask(
model="rocketqa-zh-dureader-cross-encoder",
task="text_similarity",
task_path=self.model,
max_seq_len=self.max_seq_len,
device_id=0,
)
static_results = static_taskflow(input_text)
self.assertTrue(len(static_results) == 1)
self.assertTrue("text1" in static_results[0])
self.assertTrue("text2" in static_results[0])
self.assertIsInstance(static_results[0]["similarity"], float)
input_text = ([["光眼睛大就好看吗", "眼睛好看吗？"], ["小蝌蚪找妈妈怎么样", "小蝌蚪找妈妈是谁画的"]],)
results = static_taskflow(input_text)
self.assertTrue(len(results) == 2)
for result in results:
self.assertTrue("text1" in result)
self.assertTrue("text2" in result)
self.assertIsInstance(result["similarity"], float)
# static rocketqav2 test
input_text = ([["Tomorrow is another day", "Today is a sunny day"]],)
static_taskflow = TextSimilarityTask(
model="rocketqav2-en-marco-cross-encoder",
task="text_similarity",
task_path=self.model,
max_seq_len=self.max_seq_len,
device_id=0,
)
static_results = static_taskflow(input_text)
self.assertTrue(len(static_results) == 1)
self.assertTrue("text1" in static_results[0])
self.assertTrue("text2" in static_results[0])
self.assertIsInstance(static_results[0]["similarity"], float)
input_text = (
[["Tomorrow is another day", "Today is a sunny day"], ["This is my dream", "This is my father"]],
)
results = static_taskflow(input_text)
self.assertTrue(len(results) == 2)
for result in results:
self.assertTrue("text1" in result)
self.assertTrue("text2" in result)
self.assertIsInstance(result["similarity"], float)
# static ernie-search test
input_text = ([["Tomorrow is another day", "Today is a sunny day"]],)
static_taskflow = TextSimilarityTask(
model="ernie-search-large-cross-encoder-marco-en",
task="text_similarity",
task_path=self.model,
max_seq_len=self.max_seq_len,
device_id=0,
)
static_results = static_taskflow(input_text)
self.assertTrue(len(static_results) == 1)
self.assertTrue("text1" in static_results[0])
self.assertTrue("text2" in static_results[0])
self.assertIsInstance(static_results[0]["similarity"], float)
input_text = (
[["Tomorrow is another day", "Today is a sunny day"], ["This is my dream", "This is my father"]],
)
results = static_taskflow(input_text)
self.assertTrue(len(results) == 2)
for result in results:
self.assertTrue("text1" in result)
self.assertTrue("text2" in result)
self.assertIsInstance(result["similarity"], float)
def test_taskflow_task(self):
# static rocketqav1 test
input_text = [["世界上什么东西最小", "世界上什么东西最小？"]]
static_taskflow = Taskflow(
model="rocketqa-zh-dureader-cross-encoder",
task="text_similarity",
task_path=self.model,
max_seq_len=self.max_seq_len,
)
static_results = static_taskflow(input_text)
self.assertTrue(len(static_results) == 1)
self.assertTrue("text1" in static_results[0])
self.assertTrue("text2" in static_results[0])
self.assertIsInstance(static_results[0]["similarity"], float)
# static rocketqav2 test
input_text = [["Tomorrow is another day", "Today is a sunny day"]]
static_taskflow = Taskflow(
model="rocketqav2-en-marco-cross-encoder",
task="text_similarity",
task_path=self.model,
max_seq_len=self.max_seq_len,
)
static_results = static_taskflow(input_text)
self.assertTrue(len(static_results) == 1)
self.assertTrue("text1" in static_results[0])
self.assertTrue("text2" in static_results[0])
self.assertIsInstance(static_results[0]["similarity"], float)
input_text = [["Tomorrow is another day", "Today is a sunny day"], ["This is my dream", "This is my father"]]
results = static_taskflow(input_text)
self.assertTrue(len(results) == 2)
for result in results:
self.assertTrue("text1" in result)
self.assertTrue("text2" in result)
self.assertIsInstance(result["similarity"], float)
# static ernie-search test
input_text = [["Tomorrow is another day", "Today is a sunny day"]]
static_taskflow = Taskflow(
model="ernie-search-large-cross-encoder-marco-en",
task="text_similarity",
task_path=self.model,
max_seq_len=self.max_seq_len,
)
static_results = static_taskflow(input_text)
self.assertTrue(len(static_results) == 1)
self.assertTrue("text1" in static_results[0])
self.assertTrue("text2" in static_results[0])
self.assertIsInstance(static_results[0]["similarity"], float)
input_text = [["Tomorrow is another day", "Today is a sunny day"], ["This is my dream", "This is my father"]]
results = static_taskflow(input_text)
self.assertTrue(len(results) == 2)
for result in results:
self.assertTrue("text1" in result)
self.assertTrue("text2" in result)
self.assertIsInstance(result["similarity"], float)