Commit
·
7624155
1
Parent(s):
3274db0
Upload README.md
Browse files
README.md
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
---
|
5 |
+
|
6 |
+
## PCL
|
7 |
+
Someone uses __Patronizing and Condescending Language (PCL)__ when their use of the language denotes a superior attitude towards someone else, or depicts them in a compassionate way, raising a feeling of pity among the audience.
|
8 |
+
|
9 |
+
## pcl-roberta-base model for PCL detection
|
10 |
+
This model is trained on __Don't Patronize Me!__ , a dataset of paragraphs extracted from media articles about vulnerable communities, published in 20 English-speaking countries or areas. The paragraphs have been manually annotated to assess if they contain any type of PCL.
|
11 |
+
|
12 |
+
This is the PCL detection model built on roBERTa-base.
|
13 |
+
|
14 |
+
- Git Repo: [Don't Patronize Me! official repository](https://github.com/Perez-AlmendrosC/dontpatronizeme)
|
15 |
+
- Dataset: [Available upon request here] (https://docs.google.com/forms/d/e/1FAIpQLSe5KyzXgpnEOjS-Y6Gb8TTKiWxh4_qLuPL-NGiqKCyF41ALlg/viewform)
|
16 |
+
|
17 |
+
<b>Labels</b>:
|
18 |
+
0 -> Negative;
|
19 |
+
1 -> Positive
|
20 |
+
|
21 |
+
|
22 |
+
|
23 |
+
## Example Pipeline
|
24 |
+
|
25 |
+
## Full classification example
|
26 |
+
|
27 |
+
## Output:
|
28 |
+
|
29 |
+
|
30 |
+
|
31 |
+
|
32 |
+
To know more about our work on PCL detection, the PCL detection model and the dataset, please refer to:
|
33 |
+
|
34 |
+
## Reference Papers:
|
35 |
+
|
36 |
+
|
37 |
+
```
|
38 |
+
@inproceedings{perez2020don,
|
39 |
+
title={Don’t Patronize Me! An Annotated Dataset with Patronizing and Condescending Language towards Vulnerable Communities},
|
40 |
+
author={P{\'e}rez-Almendros, Carla and Anke, Luis Espinosa and Schockaert, Steven},
|
41 |
+
booktitle={Proceedings of the 28th International Conference on Computational Linguistics},
|
42 |
+
pages={5891--5902},
|
43 |
+
year={2020}
|
44 |
+
}
|
45 |
+
```
|
46 |
+
|
47 |
+
```
|
48 |
+
@inproceedings{perez2022semeval,
|
49 |
+
title={SemEval-2022 task 4: Patronizing and condescending language detection},
|
50 |
+
author={P{\'e}rez-Almendros, Carla and Anke, Luis Espinosa and Schockaert, Steven},
|
51 |
+
booktitle={Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)},
|
52 |
+
pages={298--307},
|
53 |
+
year={2022}
|
54 |
+
}
|
55 |
+
```
|
56 |
+
|
57 |
+
```
|
58 |
+
@inproceedings{perez2022identifying,
|
59 |
+
title={Identifying condescending language: A tale of two distinct phenomena?},
|
60 |
+
author={Perez-Almendros, Carla and Schockaert, Steven},
|
61 |
+
booktitle={Proceedings of the Second Workshop on NLP for Positive Impact (NLP4PI)},
|
62 |
+
pages={130--141},
|
63 |
+
year={2022}
|
64 |
+
}
|
65 |
+
```
|