Shane Weisz commited on
Commit
e9e9957
·
1 Parent(s): e72e99e

Change wording of hate speech input

Browse files
Files changed (1) hide show
  1. app.py +2 -2
app.py CHANGED
@@ -12,11 +12,11 @@ The project is supervised by [Dr Marcus Tomalin](https://www.crassh.cam.ac.uk/ab
12
  <br/>
13
  The system is built by fine-tuning [DialoGPT](https://huggingface.co/microsoft/DialoGPT-medium#:~:text=DialoGPT%20is%20a%20SOTA%20large,single%2Dturn%20conversation%20Turing%20test) on the [MultiCONAN](https://github.com/marcoguerini/CONAN#Multitarget-CONAN) dataset, a dataset comprising a set of hate speech inputs and appropriate counterspeech responses produced under the supervision of trained NGO operators from [Stop Hate UK](https://www.stophateuk.org/).
14
  <br/><br/>
15
- **Try it out**: Enter some hate speech (or select one of the provided examples), click Submit, and see if the system generates an appropriate counterspeech response.
16
  """
17
 
18
  ARTICLE = f"""
19
- _Please note: This system is simply a prototype and cannot be guaranteed to always generate appropriate responses. Any inappropriate views or responses expressed by the system should not be construed as reflective of the views or values of the researchers._
20
 
21
 
22
  **Model:** {DEFAULT_MODEL}<br>
 
12
  <br/>
13
  The system is built by fine-tuning [DialoGPT](https://huggingface.co/microsoft/DialoGPT-medium#:~:text=DialoGPT%20is%20a%20SOTA%20large,single%2Dturn%20conversation%20Turing%20test) on the [MultiCONAN](https://github.com/marcoguerini/CONAN#Multitarget-CONAN) dataset, a dataset comprising a set of hate speech inputs and appropriate counterspeech responses produced under the supervision of trained NGO operators from [Stop Hate UK](https://www.stophateuk.org/).
14
  <br/><br/>
15
+ **Try it out**: Enter a hate speech comment (or select one of the provided examples), click Submit, and see if the system generates an appropriate counterspeech response.
16
  """
17
 
18
  ARTICLE = f"""
19
+ _Please note: This system is a prototype and cannot be guaranteed to always generate appropriate responses. Any inappropriate responses expressed by the system should not be construed as reflective of the views or values of the researchers._
20
 
21
 
22
  **Model:** {DEFAULT_MODEL}<br>