Upload model.

README.md

@@ -1,3 +1,100 @@
 ---
+
+language:
+
+- ca
+
 license: apache-2.0
+
+tags:
+
+- "catalan"
+
+- "part of speech tagging"
+
+- "pos"
+
+- "CaText"
+
+- "Catalan Textual Corpus"
+
+datasets:
+
+- "universal_dependencies"
+
+metrics:
+
+- f1
+
+inference:
+ parameters:
+ aggregation_strategy: "first"
+ 
+model-index:
+- name: roberta-base-ca-v2-cased-pos
+ results:
+ - task: 
+ type: token-classification 
+ dataset:
+ type: universal_dependencies
+ name: Ancora-ca-POS
+ metrics:
+ - name: F1
+ type: f1
+ value: 0.9909
+
+widget:
+
+- text: "Em dic Lluïsa i visc a Santa Maria del Camí." 
+
+- text: "L'Aina, la Berta i la Norma són molt amigues."
+
+- text: "El Martí llegeix el Cavall Fort."
+
 ---
+
+# Catalan BERTa-v2 (roberta-base-ca-v2) finetuned for Part-of-speech-tagging (POS)
+
+The **roberta-base-ca-v2-cased-pos** is a Part-of-speech-tagging (POS) model for the Catalan language fine-tuned from the [roberta-base-ca-v2](https://huggingface.co/projecte-aina/roberta-base-ca-v2) model, a [RoBERTa](https://arxiv.org/abs/1907.11692) base model pre-trained on a medium-size corpus collected from publicly available corpora and crawlers (check the roberta-base-ca-v2 model card for more details).
+
+## Datasets
+We used the POS dataset in Catalan from the [Universal Dependencies Treebank](https://huggingface.co/datasets/universal_dependencies) we refer to _Ancora-ca-pos_ for training and evaluation.
+
+## Evaluation and results
+We evaluated the _roberta-base-ca-v2-cased-pos_ on the Ancora-ca-ner test set against standard multilingual and monolingual baselines:
+
+| Model | Ancora-ca-pos (F1) | 
+| ------------|:-------------|
+| roberta-base-ca-v2-cased-pos |99.09 |
+| roberta-base-ca-cased-pos | **99.10** |
+| mBERT | 98.98 |
+| XLM-RoBERTa | 99.03 | 
+
+For more details, check the fine-tuning and evaluation scripts in the official [GitHub repository](https://github.com/projecte-aina/club).
+
+## Citing 
+If you use any of these resources (datasets or models) in your work, please cite our latest paper:
+```bibtex
+@inproceedings{armengol-estape-etal-2021-multilingual,
+ title = "Are Multilingual Models the Best Choice for Moderately Under-resourced Languages? {A} Comprehensive Assessment for {C}atalan",
+ author = "Armengol-Estap{\'e}, Jordi and
+ Carrino, Casimiro Pio and
+ Rodriguez-Penagos, Carlos and
+ de Gibert Bonet, Ona and
+ Armentano-Oller, Carme and
+ Gonzalez-Agirre, Aitor and
+ Melero, Maite and
+ Villegas, Marta",
+ booktitle = "Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021",
+ month = aug,
+ year = "2021",
+ address = "Online",
+ publisher = "Association for Computational Linguistics",
+ url = "https://aclanthology.org/2021.findings-acl.437",
+ doi = "10.18653/v1/2021.findings-acl.437",
+ pages = "4933--4946",
+}
+```
+
+### Funding
+This work was funded by the [Catalan Government](https://politiquesdigitals.gencat.cat/en/inici/index.html) within the framework of the [AINA project.](https://politiquesdigitals.gencat.cat/ca/economia/catalonia-ai/aina).

config.json

@@ -0,0 +1,67 @@
+{
+ "_name_or_path": "projecte-aina/roberta-base-ca-v2-cased-pos",
+ "architectures": [
+ "RobertaForTokenClassification"
+ ],
+ "attention_probs_dropout_prob": 0.1,
+ "bos_token_id": 0,
+ "eos_token_id": 2,
+ "finetuning_task": "upos",
+ "gradient_checkpointing": false,
+ "hidden_act": "gelu",
+ "hidden_dropout_prob": 0.1,
+ "hidden_size": 768,
+ "id2label": {
+ "0": "NOUN",
+ "1": "PUNCT",
+ "2": "ADP",
+ "3": "NUM",
+ "4": "SYM",
+ "5": "SCONJ",
+ "6": "ADJ",
+ "7": "PART",
+ "8": "DET",
+ "9": "CCONJ",
+ "10": "PROPN",
+ "11": "PRON",
+ "12": "X",
+ "13": "_",
+ "14": "ADV",
+ "15": "INTJ",
+ "16": "VERB",
+ "17": "AUX"
+ },
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "label2id": {
+ "NOUN": 0,
+ "PUNCT": 1,
+ "PROPN": 10,
+ "PRON": 11,
+ "X": 12,
+ "_": 13,
+ "ADV": 14,
+ "INTJ": 15,
+ "VERB": 16,
+ "AUX": 17,
+ "ADP": 2,
+ "NUM": 3,
+ "SYM": 4,
+ "SCONJ": 5,
+ "ADJ": 6,
+ "PART": 7,
+ "DET": 8,
+ "CCONJ": 9
+ },
+ "layer_norm_eps": 1e-05,
+ "max_position_embeddings": 514,
+ "model_type": "roberta",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 12,
+ "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 sha256:1c5305f84db885bba3955e10b01ce95deb7bea9e5e6b95e4f573c7e1cadba1c8
+size 496351025

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": "/gpfs/projects/bsc88/BERTs/models/roberta_base_ca_jsc/transformed_lr0.0005"}