language:
- es
license: apache-2.0
tags:
- Text2Text Generation
- Inclusive Language
- Text Neutralization
- pytorch
metrics:
- sacrebleu
model-index:
- name: es_nlp_text_neutralizer
results:
- task:
type: Text2Text Generation
name: Neutralization of texts in Spanish
metrics:
- type: sacrebleu
value: 93.8347
name: sacrebleu
- type: bertscore
value: 0.99
name: BertScoreF1
- type: DiffBleu
value: 0.38
name: DiffBleu
Model objective
The purpose of this collaboratively trained model is to create a solution that reinforces the UN objective of the gender equality.
Given any input, our model will generate a gender neutral sentence, correcting any non-inclusive expressions or words. It's a straightforward and fast solution that creates a positive impact in the contemporary social panorama.
Model specs
This model is a fine-tuned version of spanish-t5-small on the data described below. It achieves the following results on the evaluation set:
- 'eval_bleu': 93.8347,
- 'eval_f1': 0.9904,
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-04
- train_batch_size: 32
- seed: 42
- num_epochs: 10
- weight_decay: 0,01
Training and evaluation data
The data used for the model training has been manually created form a compilation of sources, obtained from a series of guidelines and manuals issued by Spanish Ministry of Health, Social Services and Equality in the matter of the usage of non-sexist language, stipulated in this linked document:
Compiled sources
Guía para un discurso igualitario en la universidad de alicante
Guía UC de Comunicación en Igualdad
Metrics
For training, we used both Blue (sacrebleu implementation in HF) and BertScore. The first one, a standard in Machine Translation processes, has been added for ensuring robustness of the newly generated data, while the second one is kept for keeping the expected semantic similarity.
However, given the actual use case, we expect generated segments to be very close to input segments and to label segments in training. As an example, we can take the following:
inputSegment = 'De acuerdo con las informaciones anteriores , las alumnas se han quejado de la actitud de los profesores en los exámenes finales. Los representantes estudiantiles son los alumnos Juanju y Javi.' expectedOutput (label) = 'De acuerdo con las informaciones anteriores, el alumnado se ha quejado de la actitud del profesorado en los exámenes finales. Los representantes estudiantiles son los alumnos Juanju y Javi.' actualOutput = 'De acuerdo con las informaciones anteriores, el alumnado se ha quejado de la actitud del profesorado en los exámenes finales. Los representantes estudiantiles son el alumnado Juanju y Javi.'
As you can see, segments are pretty similar. So, instead of measuring Bleu or BertScore here, we propose an alternate metric that would be DiffBleu:
Where the minuses as in set notation. This way, we also evaluate DiffBleu after the model has been trained.
Team Members
- Fernando Velasco (fermaat)
- Cibeles Redondo (CibelesR)
- Juan Julian Cea (Juanju)
- Magdalena Kujalowicz (MacadellaCosta)
- Javier Blasco (javiblasco)
Enjoy!