Bert Italian Cased Finetuned Pos

🚀 Italian-Bert (Italian Bert) + POS 🎃🏷

This model is a fine - tuned version of Bert Base Italian on xtreme udpos Italian for the POS downstream task. It offers high - quality performance for part - of - speech tagging in Italian.

🚀 Quick Start

The model is ready to use for POS tagging in Italian. You can follow the usage examples below to start.

✨ Features

• Fine - tuned on the xtreme udpos Italian dataset for the POS downstream task.
• Covers a wide range of POS labels, including ADJ, ADP, ADV, etc.
• Achieves high scores on evaluation metrics such as F1, Precision, and Recall.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

from transformers import pipeline

nlp_pos = pipeline(
    "ner",
    model="sachaarbonel/bert-italian-cased-finetuned-pos",
    tokenizer=(
        'sachaarbonel/bert-spanish-cased-finetuned-pos',  
        {"use_fast": False}
))


text = 'Roma è la Capitale d\'Italia.'

nlp_pos(text)
      
'''
Output:
--------
[{'entity': 'PROPN', 'index': 1, 'score': 0.9995346665382385, 'word': 'roma'},
 {'entity': 'AUX', 'index': 2, 'score': 0.9966597557067871, 'word': 'e'},
 {'entity': 'DET', 'index': 3, 'score': 0.9994786977767944, 'word': 'la'},
 {'entity': 'NOUN',
  'index': 4,
  'score': 0.9995198249816895,
  'word': 'capitale'},
 {'entity': 'ADP', 'index': 5, 'score': 0.9990894198417664, 'word': 'd'},
 {'entity': 'PART', 'index': 6, 'score': 0.57159024477005, 'word': "'"},
 {'entity': 'PROPN',
  'index': 7,
  'score': 0.9994804263114929,
  'word': 'italia'},
 {'entity': 'PUNCT', 'index': 8, 'score': 0.9772886633872986, 'word': '.'}]
'''

📚 Documentation

Details of the downstream task (POS) - Dataset

• Dataset: xtreme udpos Italian 📚

• [Fine - tune on NER script provided by @stefan - it](https://raw.githubusercontent.com/stefan-it/fine - tuned - berts - seq/master/scripts/preprocess.py)

• Labels covered:

ADJ
ADP
ADV
AUX
CCONJ
DET
INTJ
NOUN
NUM
PART
PRON
PROPN
PUNCT
SCONJ
SYM
VERB
X

Metrics on evaluation set 🧾

🔧 Technical Details

The model is a fine - tuned version of [Bert Base Italian](https://huggingface.co/dbmdz/bert - base - italian - cased) on the xtreme udpos Italian dataset for the POS downstream task. It uses the ner pipeline from the transformers library for inference.

Created by Sacha Arbonel/@sachaarbonel | [LinkedIn](https://www.linkedin.com/in/sacha - arbonel)

Made with ♥ in Paris