|
--- |
|
|
|
language: |
|
- ca |
|
|
|
license: apache-2.0 |
|
|
|
tags: |
|
- "catalan" |
|
- "paraphrase" |
|
- "textual entailment" |
|
|
|
datasets: |
|
- "projecte-aina/Parafraseja" |
|
|
|
metrics: |
|
- "combined_score" |
|
- f1 |
|
- accuracy |
|
|
|
inference: |
|
parameters: |
|
aggregation_strategy: "first" |
|
|
|
model-index: |
|
- name: roberta-large-ca-paraphrase |
|
results: |
|
- task: |
|
type: text-classification |
|
dataset: |
|
type: projecte-aina/Parafraseja |
|
name: Parafraseja |
|
metrics: |
|
- name: F1 |
|
type: f1 |
|
value: 0.86678 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.86175 |
|
- name: combined_score |
|
type: combined_score |
|
value: 0.86426 |
|
|
|
widget: |
|
|
|
- text: "Tinc un amic a Manresa. A Manresa hi viu un amic meu." |
|
- text: "La dona va anar a l'hotel en moto. Ella va agafar el cotxe per anar a l'hotel." |
|
|
|
--- |
|
|
|
# Catalan BERTa (roberta-large-ca-v2) finetuned for Paraphrase Detection |
|
|
|
## Table of Contents |
|
<details> |
|
<summary>Click to expand</summary> |
|
|
|
- [Model description](#model-description) |
|
- [Intended uses and limitations](#intended-use) |
|
- [How to use](#how-to-use) |
|
- [Limitations and bias](#limitations-and-bias) |
|
- [Training](#training) |
|
- [Training data](#training-data) |
|
- [Training procedure](#training-procedure) |
|
- [Evaluation](#evaluation) |
|
- [Variable and metrics](#variable-and-metrics) |
|
- [Evaluation results](#evaluation-results) |
|
- [Additional information](#additional-information) |
|
- [Author](#author) |
|
- [Contact information](#contact-information) |
|
- [Copyright](#copyright) |
|
- [Licensing information](#licensing-information) |
|
- [Funding](#funding) |
|
- [Citing information](#citing-information) |
|
- [Disclaimer](#disclaimer) |
|
</details> |
|
|
|
## Model description |
|
|
|
The **roberta-large-ca-paraphrase** is a Paraphrase Detection model for the Catalan language fine-tuned from the roberta-large-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. |
|
|
|
## Intended uses and limitations |
|
|
|
**roberta-large-ca-paraphrase** model can be used to detect if two sentences are in a paraphrase relation. The model is limited by its training dataset and may not generalize well for all use cases. |
|
|
|
## How to use |
|
|
|
Here is how to use this model: |
|
|
|
```python |
|
from transformers import pipeline |
|
from pprint import pprint |
|
|
|
nlp = pipeline("text-classification", model="projecte-aina/roberta-large-ca-paraphrase") |
|
example = "Tinc un amic a Manresa. </s></s> A Manresa hi viu un amic meu." |
|
|
|
paraphrase = nlp(example) |
|
pprint(paraphrase) |
|
``` |
|
|
|
## Limitations and bias |
|
At the time of submission, no measures have been taken to estimate the bias embedded in the model. However, we are well aware that our models may be biased since the corpora have been collected using crawling techniques on multiple web sources. We intend to conduct research in these areas in the future, and if completed, this model card will be updated. |
|
|
|
## Training |
|
|
|
### Training data |
|
We used the Paraphase Detection dataset in Catalan [Parafraseja](https://huggingface.co/datasets/projecte-aina/Parafraseja) for training and evaluation. |
|
|
|
### Training procedure |
|
The model was trained with a batch size of 16 and a learning rate of 5e-5 for 5 epochs. We then selected the best checkpoint using the downstream task metric in the corresponding development set and then evaluated it on the test set. |
|
|
|
## Evaluation |
|
|
|
### Variable and metrics |
|
|
|
This model was finetuned maximizing the combined_score. |
|
|
|
## Evaluation results |
|
We evaluated the _roberta-large-ca-paraphrase_ on the Parafraseja test set against standard multilingual and monolingual baselines: |
|
|
|
|
|
| Model | Parafraseja (combined_score) | |
|
| ------------|:-------------| |
|
| roberta-large-ca-v2 |**86.42** | |
|
| roberta-base-ca-v2 |84.38 | |
|
| mBERT | 79.66 | |
|
| XLM-RoBERTa | 77.83 | |
|
|
|
## Additional information |
|
|
|
### Author |
|
Text Mining Unit (TeMU) at the Barcelona Supercomputing Center (bsc-temu@bsc.es) |
|
|
|
### Contact information |
|
For further information, send an email to aina@bsc.es |
|
|
|
### Copyright |
|
Copyright (c) 2022 Text Mining Unit at Barcelona Supercomputing Center |
|
|
|
### Licensing information |
|
[Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0) |
|
|
|
### Funding |
|
This work was funded by the [Departament de la Vicepresidència i de Polítiques Digitals i Territori de la Generalitat de Catalunya](https://politiquesdigitals.gencat.cat/ca/inici/index.html#googtrans(ca|en) within the framework of [Projecte AINA](https://politiquesdigitals.gencat.cat/ca/economia/catalonia-ai/aina). |
|
|
|
### Citation Information |
|
NA |
|
|
|
### Disclaimer |
|
|
|
<details> |
|
<summary>Click to expand</summary> |
|
|
|
The models published in this repository are intended for a generalist purpose and are available to third parties. These models may have bias and/or any other undesirable distortions. |
|
|
|
When third parties, deploy or provide systems and/or services to other parties using any of these models (or using systems based on these models) or become users of the models, they should note that it is their responsibility to mitigate the risks arising from their use and, in any event, to comply with applicable regulations, including regulations regarding the use of Artificial Intelligence. |
|
|
|
In no event shall the owner and creator of the models (BSC – Barcelona Supercomputing Center) be liable for any results arising from the use made by third parties of these models. |
