pupugu02 commited on
Commit
3404d23
1 Parent(s): 3f9c99f

Add SetFit ABSA model

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
3
+ "pooling_mode_cls_token": true,
4
+ "pooling_mode_mean_tokens": false,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: setfit
3
+ tags:
4
+ - setfit
5
+ - absa
6
+ - sentence-transformers
7
+ - text-classification
8
+ - generated_from_setfit_trainer
9
+ metrics:
10
+ - accuracy
11
+ widget: []
12
+ pipeline_tag: text-classification
13
+ inference: false
14
+ ---
15
+
16
+ # SetFit Polarity Model
17
+
18
+ This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Aspect Based Sentiment Analysis (ABSA). A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification. In particular, this model is in charge of classifying aspect polarities.
19
+
20
+ The model has been trained using an efficient few-shot learning technique that involves:
21
+
22
+ 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
23
+ 2. Training a classification head with features from the fine-tuned Sentence Transformer.
24
+
25
+ This model was trained within the context of a larger system for ABSA, which looks like so:
26
+
27
+ 1. Use a spaCy model to select possible aspect span candidates.
28
+ 2. Use a SetFit model to filter these possible aspect span candidates.
29
+ 3. **Use this SetFit model to classify the filtered aspect span candidates.**
30
+
31
+ ## Model Details
32
+
33
+ ### Model Description
34
+ - **Model Type:** SetFit
35
+ <!-- - **Sentence Transformer:** [Unknown](https://huggingface.co/unknown) -->
36
+ - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
37
+ - **spaCy Model:** id_core_news_trf
38
+ - **SetFitABSA Aspect Model:** [pupugu02/C241-AB01-absa-aspect](https://huggingface.co/pupugu02/C241-AB01-absa-aspect)
39
+ - **SetFitABSA Polarity Model:** [pupugu02/C241-AB01-absa-polarity](https://huggingface.co/pupugu02/C241-AB01-absa-polarity)
40
+ - **Maximum Sequence Length:** 8192 tokens
41
+ - **Number of Classes:** 4 classes
42
+ <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
43
+ <!-- - **Language:** Unknown -->
44
+ <!-- - **License:** Unknown -->
45
+
46
+ ### Model Sources
47
+
48
+ - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
49
+ - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
50
+ - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
51
+
52
+ ## Uses
53
+
54
+ ### Direct Use for Inference
55
+
56
+ First install the SetFit library:
57
+
58
+ ```bash
59
+ pip install setfit
60
+ ```
61
+
62
+ Then you can load this model and run inference.
63
+
64
+ ```python
65
+ from setfit import AbsaModel
66
+
67
+ # Download from the 🤗 Hub
68
+ model = AbsaModel.from_pretrained(
69
+ "pupugu02/C241-AB01-absa-aspect",
70
+ "pupugu02/C241-AB01-absa-polarity",
71
+ )
72
+ # Run inference
73
+ preds = model("The food was great, but the venue is just way too busy.")
74
+ ```
75
+
76
+ <!--
77
+ ### Downstream Use
78
+
79
+ *List how someone could finetune this model on their own dataset.*
80
+ -->
81
+
82
+ <!--
83
+ ### Out-of-Scope Use
84
+
85
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
86
+ -->
87
+
88
+ <!--
89
+ ## Bias, Risks and Limitations
90
+
91
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
92
+ -->
93
+
94
+ <!--
95
+ ### Recommendations
96
+
97
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
98
+ -->
99
+
100
+ ## Training Details
101
+
102
+ ### Framework Versions
103
+ - Python: 3.10.12
104
+ - SetFit: 1.0.3
105
+ - Sentence Transformers: 3.0.0
106
+ - spaCy: 3.7.4
107
+ - Transformers: 4.36.2
108
+ - PyTorch: 2.3.0+cu121
109
+ - Datasets: 2.19.1
110
+ - Tokenizers: 0.15.2
111
+
112
+ ## Citation
113
+
114
+ ### BibTeX
115
+ ```bibtex
116
+ @article{https://doi.org/10.48550/arxiv.2209.11055,
117
+ doi = {10.48550/ARXIV.2209.11055},
118
+ url = {https://arxiv.org/abs/2209.11055},
119
+ author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
120
+ keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
121
+ title = {Efficient Few-Shot Learning Without Prompts},
122
+ publisher = {arXiv},
123
+ year = {2022},
124
+ copyright = {Creative Commons Attribution 4.0 International}
125
+ }
126
+ ```
127
+
128
+ <!--
129
+ ## Glossary
130
+
131
+ *Clearly define terms in order to be accessible across audiences.*
132
+ -->
133
+
134
+ <!--
135
+ ## Model Card Authors
136
+
137
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
138
+ -->
139
+
140
+ <!--
141
+ ## Model Card Contact
142
+
143
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
144
+ -->
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "firqaaa/indo-setfit-absa-bert-base-restaurants-polarity",
3
+ "architectures": [
4
+ "XLMRobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 8194,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.36.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 250002
28
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.2.2",
4
+ "transformers": "4.33.0",
5
+ "pytorch": "2.1.2+cu121"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": null
10
+ }
config_setfit.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "spacy_model": "id_core_news_trf",
3
+ "normalize_embeddings": false,
4
+ "span_context": 3,
5
+ "labels": [
6
+ "konflik",
7
+ "negatif",
8
+ "netral",
9
+ "positif"
10
+ ]
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f63dee23a0bf95fda64e8d449f3b986d248f47902b6bd425fe8c3c8a990cf1a
3
+ size 2271064456
model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b969a8393f074faca1b3632bbec9d7cc8f87bdee2a40bd4058c693cbcf86b58c
3
+ size 33735
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 8192,
3
+ "do_lower_case": false
4
+ }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1af481bd08ed9347cf9d3d07c24e5de75a10983819de076436400609e6705686
3
+ size 17083075
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "max_length": 8192,
50
+ "model_max_length": 8192,
51
+ "pad_to_multiple_of": null,
52
+ "pad_token": "<pad>",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
+ "sep_token": "</s>",
56
+ "sp_model_kwargs": {},
57
+ "stride": 0,
58
+ "tokenizer_class": "XLMRobertaTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "<unk>"
62
+ }