---
license: apache-2.0
base_model: bert-base-multilingual-cased
datasets:
- HiTZ/multilingual-abstrct
language:
- en
- es
- fr
- it
metrics:
- f1
pipeline_tag: token-classification
library_name: transformers
widget:
- text: In the comparison of responders versus patients with both SD (6m) and PD, responders indicated better physical well-being (P=.004) and mood (P=.02) at month 3.
- text: En la comparación de los que respondieron frente a los pacientes tanto con SD (6m) como con EP, los que respondieron indicaron un mejor bienestar físico (P=.004) y estado de ánimo (P=.02) en el mes 3.
- text: Dans la comparaison entre les répondeurs et les patients atteints de SD (6m) et de PD, les répondeurs ont indiqué un meilleur bien-être physique (P=.004) et une meilleure humeur (P=.02) au mois 3.
- text: Nel confronto tra i responder e i pazienti con SD (6m) e PD, i responder hanno indicato un migliore benessere fisico (P=.004) e umore (P=.02) al terzo mese.
---

<p align="center">
    <br>
    <img src="http://www.ixa.eus/sites/default/files/anitdote.png" style="width: 45%;">
    <be>


# mBERT for multilingual Argument Detection in the Medical Domain


This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) for the argument component 
detection task on AbstRCT data in English, Spanish, French and Italian ([https://huggingface.co/datasets/HiTZ/multilingual-abstrct](https://huggingface.co/datasets/HiTZ/multilingual-abstrct)).


## Performance

F1-macro scores (at sequence level) and their averages per test set from the argument component detection results of
monolingual, monolingual automatically post-processed, multilingual, multilingual automatically post-processed, and crosslingual experiments.

<img src="https://raw.githubusercontent.com/hitz-zentroa/multilingual-abstrct/main/resources/multilingual-abstrct-results.png" style="width: 75%;">

### Label Dictionary

````
"id2label": {
    "0": "B-Claim",
    "1": "B-Premise",
    "2": "I-Claim",
    "3": "I-Premise",
    "4": "O"
  }
````

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0

### Framework versions

- Transformers 4.40.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.2

**Contact**: [Anar Yeginbergen](https://ixa.ehu.eus/node/13807?language=en) and [Rodrigo Agerri](https://ragerri.github.io/)
HiTZ Center - Ixa, University of the Basque Country UPV/EHU