---
language:
- it
pipeline_tag: text-classification
library_name: transformers
widget:
- example_title: "Esempio 1"
  text: "colore"
- example_title: "Esempio 2"
  text: "rosso"
- example_title: "Esempio 3"
  text: "piuttosto"
 
  
---

**bert-tiny-ita-lemma-classification** is a text-classification model (based on [bert-tiny-ita](https://huggingface.co./mascIT/bert-tiny-ita)) which has been finetuned for a lemma classification task, using a private dataset of high quality dictionary data. 

It can classify an italian lemma in the following classes:
- 'AGG': 0,
- 'VERBO_INTRANSITIVO': 1,
- 'VERBO_TRANSITIVO': 2,
- 'SOST_MASCHILE': 3,
- 'SOST_FEMMINILE': 4,
- 'AVVERBIO': 5,
- 'AGG_SOSTANTIVATO': 6

The project is still a work in progress, new versions will come with time.

# Training

- epochs: 5
- lr: 1e-4
- optim: AdamW
- weight_decay: 1e-2

# Eval