language:
- en
- fr
- it
- pt
tags:
- formality
licenses:
- cc-by-nc-sa
Model Overview
This is the model presented in the paper "Detecting Text Formality: A Study of Text Classification Approaches".
The original model is mDistilBERT (base). Then, it was fine-tuned on the multilingual corpus for fomality classiication X-FORMAL that consists of 4 languages -- English (from GYAFC), French, Italian, and Brazilian Portuguese. In our experiments, the model showed the best results within Transformer-based models for the cross-lingual formality classification knowledge transfer task. More details, code and data can be found here.
Evaluation Results
Here, we provide several metrics of the best models from each category participated in the comparison to understand the ranks of values. We report accuracy score for two setups -- multilingual model fine-tuned for each language separately and then fine-tuned on all languages. For cross-lingual experiments results, please, refer to the paper.
| En | It | Po | Fr | All | |
|---|---|---|---|---|---|
| bag-of-words | 79.1 | 71.3 | 70.6 | 72.5 | --- |
| CharBiLSTM | 87.0 | 79.1 | 75.9 | 81.3 | 82.7 |
| mDistilBERT-cased | 86.6 | 76.8 | 75.9 | 79.1 | 79.4 |
| mDeBERTa-base | 87.3 | 76.6 | 75.8 | 78.9 | 79.9 |
How to use
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model_name = 'mdistilbert-base-formality-ranker'
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)
Citation
TBD
Licensing Information
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
