yangheng commited on
Commit
7de7186
1 Parent(s): 892d44b
app.py CHANGED
@@ -64,8 +64,8 @@ with demo:
64
  [![Downloads](https://pepy.tech/badge/pyabsa/month)](https://pepy.tech/project/pyabsa)
65
  """
66
  )
67
- gr.Markdown("Your input text should be no more than 80 words, that's the longest text we used in training. However, you can try longer text in self-training ")
68
- gr.Markdown("**You don't need to split each Chinese (Korean, etc.) token as the provided, just input the natural language text.**")
69
  gr.Markdown("请确保输入的文本长度不超过200词,这是训练时的最大文本长度,过长将不会获得结果")
70
  gr.Markdown("**提供的中文等其他非拉丁语系数据集采用了空格分字,这是早期数据集的遗留问题,预测时不用对中文等语言进行空格分字**")
71
  output_dfs = []
 
64
  [![Downloads](https://pepy.tech/badge/pyabsa/month)](https://pepy.tech/project/pyabsa)
65
  """
66
  )
67
+ gr.Markdown("Your input text should be no more than 80 words, that's the longest text we used in training. However, you can train your own model using 512 max length")
68
+ gr.Markdown("**You don't need to split each Chinese (Korean, etc.) token as the provided examples, just input the natural language text.**")
69
  gr.Markdown("请确保输入的文本长度不超过200词,这是训练时的最大文本长度,过长将不会获得结果")
70
  gr.Markdown("**提供的中文等其他非拉丁语系数据集采用了空格分字,这是早期数据集的遗留问题,预测时不用对中文等语言进行空格分字**")
71
  output_dfs = []
checkpoint/English/TAD/TAD-Amazon.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:add4188835c415b72dda8f8db363bb82d6217b35f6b27a1dd9d82b029594607f
3
- size 427626189
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75427d8022884a26f385289601d22b877eda3f416b829d898f773e10f0d78cb6
3
+ size 630751100
checkpoint/English/TAD/TAD-AmazonBAE.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d11d8b01f3a5275906ab136739535adb423f34da0d99ff86d5e6a96a7035333
3
- size 618481827
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c816bf76885d80fae3d8a17021e3d07339041cbcc0cb4fd24878353beb0f1ed
3
+ size 618481549
checkpoint/English/TAD/TAD-AmazonPWWS.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e46273c6c696b230e9e344db28322bb692919c6de114cea8ced8de45ee713b86
3
- size 427631136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68fca44dca3e18349b08d3c85529485c9fd43514f4e94146804db17959a0be8e
3
+ size 621707291
checkpoint/English/TAD/TAD-AmazonTextFooler.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a4115d2d190f02cfd2cda0830ab013f011263d5b88129a0d997876f29ce6aa7
3
- size 628172415
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:870fb9f96228793ef727bb71130b41c16b3e3b3e6adc616d42f95d85dbbfc1f6
3
+ size 628174331
checkpoint/English/TAD/TAD-BERT-Amazon.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:383bf63ad88b690c894c4bbc29a8e9c0ac6175cea5e88bff1db197f06b8509c8
3
- size 427631665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df1654efcfe101de7e42e134b55c4f37f7ffd37c6c1d5ef07295364e7b65337b
3
+ size 427627904
checkpoint/English/TAD/TAD-BERT-AmazonBAE.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d700f72bc54f6931e83750d5d6850a77baf385effcb3b71b615b3009b3fd719a
3
- size 427631668
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e8f2d39b40622153c4f7f8f3128e0a2aecd6fa71d59ec5cda22189d39b9d170
3
+ size 427633731
checkpoint/English/TAD/TAD-BERT-AmazonPWWS.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:987a05b58a54ea533974be1fe943e7f069ec816eed23a4d57752950e705d7c63
3
- size 427631162
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40a51b5bf114f91e7909f6dc7d3d274e717ca4f38b7b2ff26a172ecf035bd4df
3
+ size 427628535
checkpoint/English/TAD/TAD-BERT-AmazonTextFooler.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb8df1636dfa782a18ce09a7f4ececbcab83bbe68ae01f75bf0bed2e3b63d6ea
3
- size 427630967
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:927b1cd28052c22377243a96f5d45a280cda44d878e83d9d9b4ca6381cbdd249
3
+ size 427631361
release-note.json CHANGED
@@ -1,4 +1,104 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "1.10.4": {
3
  "1": "Fix a bug in dataset detection, which may cause unexpected dataset mis-detection"
4
  },
@@ -458,4 +558,4 @@
458
  "2": "Add polarity label-fix features for some datasets containing negative labels",
459
  "3": "Some typo-fix"
460
  }
461
- }
 
1
  {
2
+ "1.16.6": {
3
+ "1": "Update findfile dependency to 1.7.9.7",
4
+ "2": ""
5
+ },
6
+ "1.16.5": {
7
+ "1": "Modify some output printing",
8
+ "2": "Fix offline pretrained model loading for text classification"
9
+ },
10
+ "1.16.4": {
11
+ "1": "Add validation set support for ATEPC",
12
+ "2": "Other improvements"
13
+ },
14
+ "1.16.3": {
15
+ "1": "fix patch for 1.16.2"
16
+ },
17
+ "1.16.2": {
18
+ "1": "fix a dataset detection issue",
19
+ "2": "Add probability distribution and confidence to the sentiment classification in ATEPC model",
20
+ "3": "Add a experimental feature to automatic annotate the APC amd ATEPC dataset using aspect extractor provided by PyABSA, see demos/aspect_text_extraction/extract_aspect_and_make_dataset.py"
21
+ },
22
+ "1.16.1": {
23
+ "1": "fix some DatasetItem"
24
+ },
25
+ "1.16.0": {
26
+ "1": "Fix a checkpoint downloading and inflation bug which prevents loading a checkpoint from huggingface spaces",
27
+ "2": "Fix a important bug which cause unexpected low performance when performing ATEPC inference for Chinese language (and possibly other non-latin languages)",
28
+ "3": "Minor modifications"
29
+ },
30
+ "1.15.7": {
31
+ "1": "Update findfile dependency to 1.7.9.5",
32
+ "2": "Default to activate use_bert_spc for ATEPC models to improve ATE and APC performance",
33
+ "3": "Minor fixes"
34
+ },
35
+ "1.15.6": {
36
+ "1": "Add classification report (including precision, recall, F1) display after training, set config.show_metric to activate",
37
+ "2": "Add offline option to load huggingface model in inference: set get_xxx(offline=True) to auto detect and load local pretrained model",
38
+ "3": "Fix lcf-fusion in fast-lsa-t-v2",
39
+ "4": "Fix some typos",
40
+ "5": "Rename MOOC-En dataset to MOOC_En"
41
+ },
42
+ "1.15.5": {
43
+ "1": "Minor fixes of tad inference"
44
+ },
45
+ "1.15.4": {
46
+ "1": "Fix some bugs",
47
+ "2": "Add some new features",
48
+ "3": "Add a english MOOC dataset"
49
+ },
50
+ "1.15.0": {
51
+ "1": "Fix some bugs"
52
+ },
53
+ "1.14.8": {
54
+ "1": "Minor fixes"
55
+ },
56
+ "1.14.7": {
57
+ "1": "Refactor optimizer support, you can use torch optimizer either by a string or an optimizer object from torch.optim",
58
+ "2": "Fix checkpoint saving in some scenarios",
59
+ "3": "Minor fixes"
60
+ },
61
+ "1.14.6": {
62
+ "1": "Minor fixes"
63
+ },
64
+ "1.14.5": {
65
+ "1": "Revert Python version dependency",
66
+ "2": "Revert Torch dependency"
67
+ },
68
+ "1.14.4": {
69
+ "1": "This version contain breaking experimental changes, if you find any bug please roll back and report on Github"
70
+ },
71
+ "1.14.3(2)": {
72
+ "1": "Refactor pre-tokenization before inference for multilingual ATEPC",
73
+ "2": "Reset default checkpoint host to Huggingface Hub (useful for Chinese users), please test and report if it works",
74
+ "3": "Other bug fixes and improvement, see source code"
75
+ },
76
+ "1.14.1": {
77
+ "1": "Minor update"
78
+ },
79
+ "1.14.0": {
80
+ "1": "Bug fixes"
81
+ },
82
+ "1.13.4": {
83
+ "1": "Refactor output save format",
84
+ "2": "Register SemEval2016Task5 datasets in PyABSA",
85
+ "3": "Add More language support for ATEPC"
86
+ },
87
+ "1.13.3": {
88
+ "1": "Improve quality of aspect term extraction results"
89
+ },
90
+ "1.13.0(1,2)": {
91
+ "1": "Bug Fixes"
92
+ },
93
+ "1.10.6": {
94
+ "1": "Fix latent resource warning"
95
+ },
96
+ "1.10.5": {
97
+ "1": "Fix config check function",
98
+ "2": "Fix inference of baseline APC models",
99
+ "3": "Some refactor, run tests and improve stability",
100
+ "4": "Remove SSW APC models"
101
+ },
102
  "1.10.4": {
103
  "1": "Fix a bug in dataset detection, which may cause unexpected dataset mis-detection"
104
  },
 
558
  "2": "Add polarity label-fix features for some datasets containing negative labels",
559
  "3": "Some typo-fix"
560
  }
561
+ }