fermaat commited on
Commit
ad23043
1 Parent(s): 129a6eb

include descriptions

Browse files
Files changed (1) hide show
  1. app.py +19 -1
app.py CHANGED
@@ -16,7 +16,24 @@ model = AutoModelForSeq2SeqLM.from_pretrained(model_checkpoint)
16
  model.config.max_length = 512
17
  model.to(device)
18
 
 
19
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
20
 
21
  def postproc(input_sentence, preds):
22
  try:
@@ -77,7 +94,8 @@ examples=['De acuerdo con las informaciones anteriores , las alumnas se han quej
77
 
78
  iface = gr.Interface(fn=get_output,
79
  title="Spanish Text Neutralization app",
80
- description="The purpose of this app is to transform Spanish gendered text into a neutral version, suitable for an unbiased environment",
 
81
  examples=examples,
82
  # inputs="text",
83
  inputs=gr.inputs.Textbox(label="Introduce some Spanish text here"),
 
16
  model.config.max_length = 512
17
  model.to(device)
18
 
19
+ article = """
20
 
21
+ <p style="text-align: justify;">
22
+
23
+ Spanish is a beautiful language and it has many ways of referring to people, neutralizing the genders and using some of the resources inside the language. One would say *Todas las personas asistentes* instead of *Todos los asistentes* and it would end in a more inclusive way for talking about people.
24
+
25
+ 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.
26
+
27
+ <p align="center">
28
+ <img src="https://upload.wikimedia.org/wikipedia/commons/2/29/Gender_equality_symbol_%28clipart%29.png" width="250"/>
29
+ </p>
30
+
31
+ One of the toughest challenges when building the app and the model was to find proper data for training the model. Therefore, the team opted to dedicate a considerable amount of time to build it from the scratch. These data has been 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](https://www.inmujeres.gob.es/servRecursos/formacion/GuiasLengNoSexista/docs/Guiaslenguajenosexista_.pdf). You can take a look at some details of the process in the linked dataset
32
+
33
+ </p>
34
+ """
35
+
36
+ description = "The purpose of this app is to transform Spanish gendered text into a neutral version, suitable for an unbiased environment"
37
 
38
  def postproc(input_sentence, preds):
39
  try:
 
94
 
95
  iface = gr.Interface(fn=get_output,
96
  title="Spanish Text Neutralization app",
97
+ description=description,
98
+ article=article,
99
  examples=examples,
100
  # inputs="text",
101
  inputs=gr.inputs.Textbox(label="Introduce some Spanish text here"),