Commit
•
4e5bc91
1
Parent(s):
9b34583
Initial commit
Browse files- README.md +44 -0
- config.json +65 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- es
|
4 |
+
license: apache-2.0
|
5 |
+
tags:
|
6 |
+
- "national library of spain"
|
7 |
+
- "spanish"
|
8 |
+
- "bne"
|
9 |
+
- "capitel"
|
10 |
+
- "ner"
|
11 |
+
datasets:
|
12 |
+
- "bne"
|
13 |
+
- "capitel"
|
14 |
+
metrics:
|
15 |
+
- "f1"
|
16 |
+
|
17 |
+
---
|
18 |
+
|
19 |
+
# Spanish RoBERTa-base trained on BNE finetuned for CAPITEL Named Entity Recognition (NER) dataset.
|
20 |
+
RoBERTa-base-bne is a transformer-based masked language model for the Spanish language. It is based on the [RoBERTa](https://arxiv.org/abs/1907.11692) base model and has been pre-trained using the largest Spanish corpus known to date, with a total of 570GB of clean and deduplicated text processed for this work, compiled from the web crawlings performed by the [National Library of Spain (Biblioteca Nacional de España)](http://www.bne.es/en/Inicio/index.html) from 2009 to 2019.
|
21 |
+
|
22 |
+
Original pre-trained model can be found here: https://huggingface.co/BSC-TeMU/roberta-base-bne
|
23 |
+
|
24 |
+
## Dataset
|
25 |
+
The dataset used is the one from the [CAPITEL competition at IberLEF 2020](https://sites.google.com/view/capitel2020) (sub-task 1).
|
26 |
+
|
27 |
+
## Evaluation and results
|
28 |
+
F1 Score: 0.8959
|
29 |
+
|
30 |
+
For evaluation details visit our [GitHub repository](https://github.com/PlanTL-SANIDAD/lm-spanish).
|
31 |
+
|
32 |
+
|
33 |
+
## Citing
|
34 |
+
Check out our paper for all the details: https://arxiv.org/abs/2107.07253
|
35 |
+
```
|
36 |
+
@misc{gutierrezfandino2021spanish,
|
37 |
+
title={Spanish Language Models},
|
38 |
+
author={Asier Gutiérrez-Fandiño and Jordi Armengol-Estapé and Marc Pàmies and Joan Llop-Palao and Joaquín Silveira-Ocampo and Casimiro Pio Carrino and Aitor Gonzalez-Agirre and Carme Armentano-Oller and Carlos Rodriguez-Penagos and Marta Villegas},
|
39 |
+
year={2021},
|
40 |
+
eprint={2107.07253},
|
41 |
+
archivePrefix={arXiv},
|
42 |
+
primaryClass={cs.CL}
|
43 |
+
}
|
44 |
+
```
|
config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "../models/bne-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"finetuning_task": "ner",
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.0,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "B_OTH",
|
16 |
+
"1": "I_OTH",
|
17 |
+
"2": "E_OTH",
|
18 |
+
"3": "S_ORG",
|
19 |
+
"4": "S_OTH",
|
20 |
+
"5": "B_PER",
|
21 |
+
"6": "E_PER",
|
22 |
+
"7": "B_ORG",
|
23 |
+
"8": "E_ORG",
|
24 |
+
"9": "S_LOC",
|
25 |
+
"10": "S_PER",
|
26 |
+
"11": "B_LOC",
|
27 |
+
"12": "E_LOC",
|
28 |
+
"13": "I_PER",
|
29 |
+
"14": "I_ORG",
|
30 |
+
"15": "I_LOC",
|
31 |
+
"16": "O"
|
32 |
+
},
|
33 |
+
"initializer_range": 0.02,
|
34 |
+
"intermediate_size": 3072,
|
35 |
+
"label2id": {
|
36 |
+
"B_OTH": 0,
|
37 |
+
"I_OTH": 1,
|
38 |
+
"E_OTH": 2,
|
39 |
+
"S_ORG": 3,
|
40 |
+
"S_OTH": 4,
|
41 |
+
"B_PER": 5,
|
42 |
+
"E_PER": 6,
|
43 |
+
"B_ORG": 7,
|
44 |
+
"E_ORG": 8,
|
45 |
+
"S_LOC": 9,
|
46 |
+
"S_PER": 10,
|
47 |
+
"B_LOC": 11,
|
48 |
+
"E_LOC": 12,
|
49 |
+
"I_PER": 13,
|
50 |
+
"I_ORG": 14,
|
51 |
+
"I_LOC": 15,
|
52 |
+
"O": 16
|
53 |
+
},
|
54 |
+
"layer_norm_eps": 1e-05,
|
55 |
+
"max_position_embeddings": 514,
|
56 |
+
"model_type": "roberta",
|
57 |
+
"num_attention_heads": 12,
|
58 |
+
"num_hidden_layers": 12,
|
59 |
+
"pad_token_id": 1,
|
60 |
+
"position_embedding_type": "absolute",
|
61 |
+
"transformers_version": "4.6.1",
|
62 |
+
"type_vocab_size": 1,
|
63 |
+
"use_cache": true,
|
64 |
+
"vocab_size": 50262
|
65 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3793b143635ec31d9848367e697c0a6965f56eb4b3ce7872612986a8851ad67
|
3 |
+
size 496347953
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "../models/bne-base"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|