|
--- |
|
language: pt |
|
tags: |
|
- seq2seq |
|
- t5 |
|
- positive_perspectives |
|
datasets: |
|
- dominguesm/positive-reframing-ptbr-dataset |
|
widget: |
|
- text: "['growth', 'neutralizing']: Sempre estressado e pensando em um monte de coisas ao mesmo tempo, preciso levar uma de cada vez, sobrecarga estressada, necessidade de reclamar" |
|
- text: "['growth', 'neutralizing', 'optimism']: Se eu não tiver um colapso mental antes do final do verão, será um milagre." |
|
- text: "['impermanence']: Dirigindo para visitar a vovó no hospital e o meu filho que está doente." |
|
- text: "['optimism']: Ótimo agora, como vou explicar isso para ela, ela está tão perto de mim que não posso perdê-la :'(" |
|
- text: "['growth', 'optimism']: sempre há algo que eu poderia estar fazendo. Eu geralmente escolho não fazer isso." |
|
--- |
|
|
|
# Positive Perspectives with Portuguese Text Reframing |
|
|
|
## Model description |
|
|
|
This model is a [PTT5](https://huggingface.co/unicamp-dl/ptt5-base-portuguese-vocab) adjusted to the sentiment transfer task, where the objective is to reverse the sentiment polarity of a text without contradicting the original meaning. Positive reframing induces a complementary positive viewpoint (e.g. glass-half-full) escaping negative patterns. Based on the article [arXiv:2204.02952](https://arxiv.org/abs/2204.02952). |
|
|
|
## How to use |
|
|
|
The model uses one or more sentiment strategies concatenated with a sentence and will generate a sentence with the applied sentiment output. The maximum string length is 1024 tokens. Entries must be organized in the following format: |
|
|
|
``` |
|
"['thankfulness', 'optimism']: Tenho tanta coisa para fazer antes de sair da cidade por uma semana no domingo." |
|
``` |
|
|
|
### Available sentiment strategies: |
|
|
|
**growth**: viewing a challenging event as an opportunity for the author to specifically grow or improve himself. |
|
|
|
**impermanence**: Saying that bad things don't last forever, will get better soon, and/or that other people have had similar difficulties. |
|
|
|
**neutralizing**: Replacing a negative word with a neutral word. For example, “This was a terrible day” becomes “This was a long day”. |
|
|
|
**optimism**: Focusing on things about the situation itself, at that moment, that are good (not just predicting a better future). |
|
|
|
**self_affirmation**: Talking about what strengths the author already has, or values he admires, such as love, courage, perseverance, etc. |
|
|
|
**thankfulness**: Expressing gratitude or gratitude with keywords like appreciate, happy for it, grateful for, good thing, etc. |
|
|
|
### Usage |
|
|
|
```python |
|
from transformers import pipeline |
|
|
|
pipe = pipeline('summarization', "dominguesm/positive-reframing-ptbr") |
|
|
|
text = "['thankfulness', 'optimism']: Tenho tanta coisa para fazer antes de sair da cidade por uma semana no domingo." |
|
|
|
pipe(text, max_length=1024) |
|
|
|
``` |
