rebeccaqian commited on
Commit
d67ae66
·
1 Parent(s): e1417b6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +31 -15
README.md CHANGED
@@ -67,39 +67,55 @@ The perturber is a finetuned BART model (Lewis et al., 2020) with 24 layers, 102
67
 
68
  This model release is separately trained using the HuggingFace transformers library, with the same parameters as the ParlAI model.
69
 
70
- Currently the perturber supports text rewriting along three axes and several attributes:
71
- - **gender:** man, woman, non-binary
72
- - **race:** black, white, asian, hispanic, native-american, pacific-islander
73
- - **age:** child, young, middle-aged, senior, adult
74
-
75
  ### Uses
76
 
77
  The perturber is intended for use by fairness researchers and engineers working on demographic debiasing applications. The perturber is a controllable generation model that given a word, target demographic attribute and input text, outputs text where the selected word and associated references are rewritten to the target demographic attribute. Control variables and the input text are separated by a <PERT_SEP> token.
78
 
79
  ## Examples
 
 
 
80
 
81
- Input:
 
 
 
 
 
 
82
  his, woman <PERT_SEP> Jack was passionate about rock climbing and his love for the sport was infectious to all men around him.
83
 
84
- Output:
85
- Jackie was passionate about rock climbing and her love for the sport was infectious to all men around her.
 
86
 
87
- Input:
88
  Alice, man <PERT_SEP> To her girlfriend Jen, Alice was a doting mother, loving girlfriend and talented actress.
89
 
90
- Output:
91
  To his girlfriend Jen, Alan was a doting father, loving partner and talented actor.
92
-
93
- Input:
 
 
 
 
 
 
 
 
 
 
94
  child, senior <PERT_SEP> The young child is naive and his innocence must be protected at all costs.
95
 
96
- Output:
97
  The elderly person is naive and his innocence must be protected at all costs.
98
 
99
- Input:
 
100
  Asian, black <PERT_SEP> The Asian students association often hosted anime nights and boba events on campus.
101
 
102
- Output:
103
  The Black students association often hosted anime nights and boba events on campus.
104
 
105
  ### Contributions
 
67
 
68
  This model release is separately trained using the HuggingFace transformers library, with the same parameters as the ParlAI model.
69
 
 
 
 
 
 
70
  ### Uses
71
 
72
  The perturber is intended for use by fairness researchers and engineers working on demographic debiasing applications. The perturber is a controllable generation model that given a word, target demographic attribute and input text, outputs text where the selected word and associated references are rewritten to the target demographic attribute. Control variables and the input text are separated by a <PERT_SEP> token.
73
 
74
  ## Examples
75
+ Below we show some example inputs and outputs for the perturber rewriting text along different demographic axes and attributes.
76
+
77
+ Model inputs follow the format `[selected_word][target_attribute] <PERT_SEP> [input_text]`, where `selected_word` is a word that contains demographic information, `target_attribute` is a demographic attribute such as "man" or "asian", and `input_text` is the text sequence to rewrite.
78
 
79
+ Currently the perturber supports text rewriting along three axes and several attributes:
80
+ - **gender:** man, woman, non-binary
81
+ - **race:** black, white, asian, hispanic, native-american, pacific-islander
82
+ - **age:** child, young, middle-aged, senior, adult
83
+
84
+ ### Gender
85
+ _Input:_
86
  his, woman <PERT_SEP> Jack was passionate about rock climbing and his love for the sport was infectious to all men around him.
87
 
88
+ _Output:_
89
+ Jackie was passionate about rock climbing and her love for the sport was infectious to all men around her.
90
+ <br/>
91
 
92
+ _Input:_
93
  Alice, man <PERT_SEP> To her girlfriend Jen, Alice was a doting mother, loving girlfriend and talented actress.
94
 
95
+ _Output:_
96
  To his girlfriend Jen, Alan was a doting father, loving partner and talented actor.
97
+ <br/>
98
+ <br/>
99
+
100
+ _Input:_
101
+ his, non-binary <PERT_SEP> Jack was passionate about rock climbing and his love for the sport was infectious to all men around him.
102
+
103
+ _Output:_
104
+ Jack was passionate about rock climbing and their love for the sport was infectious to all men around them.
105
+ <br/>
106
+ <br/>
107
+ ### Age
108
+ _Input:_
109
  child, senior <PERT_SEP> The young child is naive and his innocence must be protected at all costs.
110
 
111
+ _Output:_
112
  The elderly person is naive and his innocence must be protected at all costs.
113
 
114
+ ### Race/Ethnicity
115
+ _Input:_
116
  Asian, black <PERT_SEP> The Asian students association often hosted anime nights and boba events on campus.
117
 
118
+ _Output:_
119
  The Black students association often hosted anime nights and boba events on campus.
120
 
121
  ### Contributions