Initial commit

README.md

@@ -0,0 +1,49 @@
+---
+language:
+- es
+license: apache-2.0
+tags:
+- "national library of spain"
+- "spanish"
+- "bne"
+- "capitel"
+- "pos"
+datasets:
+- "bne"
+- "capitel"  
+metrics:
+- "f1"
+widget:
+- text: "Festival de San Sebastián: Johnny Depp recibirá el premio Donostia en pleno rifirrafe judicial con Amber Heard" 
+- text: "El alcalde de Vigo, Abel Caballero, ha comenzado a colocar las luces de Navidad en agosto."
+- text: "Gracias a los datos de la BNE, se ha podido lograr este modelo del lenguaje."
+- text: "El Tribunal Superior de Justicia se pronunció ayer: \"Hay base legal dentro del marco jurídico actual\"."
+
+---
+
+# Spanish RoBERTa-large trained on BNE finetuned for CAPITEL Part of Speech (POS) dataset
+RoBERTa-large-bne is a transformer-based masked language model for the Spanish language. It is based on the [RoBERTa](https://arxiv.org/abs/1907.11692) large 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.
+
+Original pre-trained model can be found here: https://huggingface.co/BSC-TeMU/roberta-large-bne
+
+## Dataset
+The dataset used is the one from the [CAPITEL competition at IberLEF 2020](https://sites.google.com/view/capitel2020) (sub-task 2).
+
+## Evaluation and results
+F1 Score: 0.9851 (average of 5 runs).
+
+For evaluation details visit our [GitHub repository](https://github.com/PlanTL-SANIDAD/lm-spanish).
+
+
+## Citing 
+Check out our paper for all the details: https://arxiv.org/abs/2107.07253
+```
+@misc{gutierrezfandino2021spanish,
+      title={Spanish Language Models}, 
+      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},
+      year={2021},
+      eprint={2107.07253},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "../models/bne-large",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "pos",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "NUM",
+    "1": "VERB",
+    "2": "X",
+    "3": "ADV",
+    "4": "PRON",
+    "5": "INTJ",
+    "6": "ADJ",
+    "7": "PUNCT",
+    "8": "ADP",
+    "9": "SCONJ",
+    "10": "NOUN",
+    "11": "PROPN",
+    "12": "CCONJ",
+    "13": "DET"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "NUM": 0,
+    "VERB": 1,
+    "X": 2,
+    "ADV": 3,
+    "PRON": 4,
+    "INTJ": 5,
+    "ADJ": 6,
+    "PUNCT": 7,
+    "ADP": 8,
+    "SCONJ": 9,
+    "NOUN": 10,
+    "PROPN": 11,
+    "CCONJ": 12,
+    "DET": 13
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cf7c94c33ae66954fe4667caa96a3964d09d144bce679301e170ced3b2b1096
+size 1417449073

special_tokens_map.json

@@ -0,0 +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_config.json

@@ -0,0 +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-large"}