finiteautomata commited on
Commit
91676c9
1 Parent(s): 740571f

First version of robertuito

Browse files
README.md ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Sentiment Analysis in Spanish
2
+ ## robertuito-sentiment-analysis
3
+
4
+ Repository: [https://github.com/pysentimiento/pysentimiento/](https://github.com/finiteautomata/pysentimiento/)
5
+
6
+
7
+ Model trained with TASS 2020 corpus (around ~5k tweets) of several dialects of Spanish. Base model is [RoBERTuito](https://github.com/pysentimiento/robertuito), a RoBERTa model trained in Spanish tweets.
8
+
9
+ Uses `POS`, `NEG`, `NEU` labels.
10
+
11
+
12
+ ## Results
13
+
14
+ Results for the four tasks evaluated in `pysentimiento`. Results are expressed as Macro F1 scores
15
+
16
+
17
+ | model | emotion | hate_speech | irony | sentiment |
18
+ |:--------------|:--------------|:--------------|:--------------|:--------------|
19
+ | robertuito | 0.560 ± 0.010 | 0.759 ± 0.007 | 0.739 ± 0.005 | 0.705 ± 0.003 |
20
+ | roberta | 0.527 ± 0.015 | 0.741 ± 0.012 | 0.721 ± 0.008 | 0.670 ± 0.006 |
21
+ | bertin | 0.524 ± 0.007 | 0.738 ± 0.007 | 0.713 ± 0.012 | 0.666 ± 0.005 |
22
+ | beto_uncased | 0.532 ± 0.012 | 0.727 ± 0.016 | 0.701 ± 0.007 | 0.651 ± 0.006 |
23
+ | beto_cased | 0.516 ± 0.012 | 0.724 ± 0.012 | 0.705 ± 0.009 | 0.662 ± 0.005 |
24
+ | mbert_uncased | 0.493 ± 0.010 | 0.718 ± 0.011 | 0.681 ± 0.010 | 0.617 ± 0.003 |
25
+ | biGRU | 0.264 ± 0.007 | 0.592 ± 0.018 | 0.631 ± 0.011 | 0.585 ± 0.011 |
26
+
27
+
28
+ Note that for Hate Speech, these are the results for Semeval 2019, Task 5 Subtask B
29
+
30
+ ## Citation
31
+
32
+ If you use this model in your research, please cite pysentimiento and RoBERTuito papers:
33
+
34
+ ```
35
+ @misc{perez2021pysentimiento,
36
+ title={pysentimiento: A Python Toolkit for Sentiment Analysis and SocialNLP tasks},
37
+ author={Juan Manuel Pérez and Juan Carlos Giudici and Franco Luque},
38
+ year={2021},
39
+ eprint={2106.09462},
40
+ archivePrefix={arXiv},
41
+ primaryClass={cs.CL}
42
+ }
43
+ @misc{perez2021robertuito,
44
+ title={RoBERTuito: a pre-trained language model for social media text in Spanish},
45
+ author={Juan Manuel Pérez and Damián A. Furman and Laura Alonso Alemany and Franco Luque},
46
+ year={2021},
47
+ eprint={2111.09453},
48
+ archivePrefix={arXiv},
49
+ primaryClass={cs.CL}
50
+ }
51
+ ```
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pysentimiento/robertuito-base-uncased",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "NEG",
16
+ "1": "NEU",
17
+ "2": "POS"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "NEG": 0,
23
+ "NEU": 1,
24
+ "POS": 2
25
+ },
26
+ "layer_norm_eps": 1e-12,
27
+ "max_position_embeddings": 130,
28
+ "model_type": "roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 1,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.11.3",
36
+ "type_vocab_size": 1,
37
+ "use_cache": true,
38
+ "vocab_size": 30002
39
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c09a0038e4456ae5ff46a780cc37449191c71497ae6bf56283b610145ac7a46c
3
+ size 435246509
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}
test_results.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "test_loss": 0.9389793872833252,
3
+ "test_neg_f1": 0.7858959145617902,
4
+ "test_neg_precision": 0.7831081081081082,
5
+ "test_neg_recall": 0.7887036406941137,
6
+ "test_neu_f1": 0.5708963911525029,
7
+ "test_neu_precision": 0.5264061829111206,
8
+ "test_neu_recall": 0.6236012207527976,
9
+ "test_pos_f1": 0.7628057221965852,
10
+ "test_pos_precision": 0.8369620253164557,
11
+ "test_pos_recall": 0.7007206443408224,
12
+ "test_micro_f1": 0.7154460352422908,
13
+ "test_acc": 0.7154460352422908,
14
+ "test_macro_f1": 0.7065326571464539,
15
+ "test_macro_precision": 0.7154920697212219,
16
+ "test_macro_recall": 0.7043418884277344,
17
+ "test_runtime": 9.0426,
18
+ "test_samples_per_second": 803.305,
19
+ "test_steps_per_second": 50.207
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": "models/twerto-base-uncased/special_tokens_map.json", "name_or_path": "pysentimiento/robertuito-base-uncased", "tokenizer_class": "PreTrainedTokenizerFast"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73e12e93645ff390c7c7162b01f620d8e28cb70ab82a9316d565de9c9e6254f7
3
+ size 2799