|
--- |
|
language: en |
|
license: cc-by-4.0 |
|
tags: |
|
- seq2seq |
|
- t5 |
|
- positive_perspectives |
|
widget: |
|
- text: "['neutralizing', 'optimism']: Ugh I have to wake up so early (9:00) and go to class (a massage). I have so much (so little) to do today." |
|
- text: "['growth']: You know I really don't care about the power struggle between the papacy and secular authority in the medieval ages. stupid" |
|
- text: "['neutralizing', 'optimism']: thinking about my future makes me want to go live on a island alone forever. annoyed" |
|
- text: "['neutralizing', 'optimism']: Honestly don't know how I'm going to finish all of this homework and projects! homework FAIL Tired FML" |
|
- text: "['neutralizing', 'optimism', 'thankfulness']: Who would have ever guessed that it would be so freaking hard to get three different grades from two different schools together." |
|
--- |
|
|
|
# Positive Perspectives with English Text Reframing |
|
|
|
## Model description |
|
|
|
This model is a [T5-base](https://huggingface.co/t5-base) 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: |
|
|
|
**Input**: |
|
``` |
|
['growth']: totally fed up with this bid now! :-( haven't even thought about my presentation yet :-( |
|
``` |
|
|
|
### Available sentiment strategies: |
|
|
|
| Strategy | Description | |
|
| --------- | ----------- | |
|
|**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-en") |
|
|
|
text = "['growth']: totally fed up with this bid now! :-( haven't even thought about my presentation yet :-(" |
|
|
|
pipe(text, max_length=1024) |
|
|
|
``` |
|
|
|
**Output**: |
|
|
|
``` |
|
# I haven't thought about my presentation yet, but I'm going to work hard to improve #my presentation, and I'll be better soon. |
|
``` |
