|
Size: 3530
Comment:
|
Size: 3628
Comment:
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 58: | Line 58: |
| ||'''Method''' ||'''STA'''||'''CS'''||'''WO'''||'''BLEU'''||'''PPL'''||'''GM'''|| ||**Duplicate**||0.38 ||1 ||1 ||1 ||146.86||1.78 || ||**Delete** ||1 ||0.93 ||0.84 ||0.92 ||246.80||4.14 || ||**GPT-2** ||0.90 ||0.86 ||0.71 ||0.86 ||258.44||3.71 || ||**GPT-3** ||0.88 ||0.92 ||0.79 ||0.92 ||359.12||3.58 || ||**T-5 base** ||0.90 ||0.97 ||0.85 ||0.95 ||187.03||4.10 || ||**T-5 large**||0.93 ||0.97 ||0.86 ||0.95 ||170.02||4.31 || |
||'''Method''' ||'''STA'''||'''CS'''||'''WO'''||'''BLEU'''||'''PPL'''||'''GM'''|| ||'''Duplicate'''|| 0.38 || 1.00 || 1.00 || 1.00 || 146.86 || 1.78 || ||'''Delete''' || 1.00 || 0.93 || 0.84 || 0.92 || 246.80 || 4.14 || ||'''GPT-2''' || 0.90 || 0.86 || 0.71 || 0.86 || 258.44 || 3.71 || ||'''GPT-3''' || 0.88 || 0.92 || 0.79 || 0.92 || 359.12 || 3.58 || ||'''T-5 base''' || 0.90 || 0.97 || 0.85 || 0.95 || 187.03 || 4.10 || ||'''T-5 large'''|| 0.93 || 0.97 || 0.86 || 0.95 || 170.02 || 4.31 || |
Devulgarization of Polish Texts
DEPOT is a text style transfer framework for replacing vulgar expressions in Polish utterances with their non-vulgar equivalents while preserving the main characteristics of the text. The framework contains three pre-trained language models (GPT-2, GPT-3 and T-5) trained on a newly created parallel corpus of sentences containing vulgar expressions and their equivalents. The resulting models are evaluated by checking style transfer accuracy, content preservation and language quality.
Download
Download link
Archive (4.1 GB)
Contents of the archive
data/train_corpus_raw.xlsx – the corpus of texts, which contain vulgar expressions, their euphemistic substitutes and contexts.
data/train_corpus_preprocessed.tsv – the preprocessed parallel corpus of vulgar and non-vulgar texts used to train the models.
data/evaluation_corpus.txt – the corpus used to evaluate the models, originally published by Grochowski (2008).
data/evaluation_results_sentences.tsv – original texts and texts processed by the models.
data/evaluation_results_metrics.tsv – automatic evaluatoin results.
Requirements
Required packages can be installed by running:
pip3 install -r requirements.txt
Additionally, in order to run evaluation scripts, please install Przetak and update the value of the GOPATH variable in evaluation/__init__.py file.
Usage
The notebooks/ directory contains examples of inference and evaluation.
Evaluation might be run from the command line:
python3 -m evaluation -o <original texts> -t <transfered texts>
Evaluation
The performance of the models was assessed in three categories using automatic metrics.
Style transfer accuracy (STA) was assessed using Przetak
Preservation of the content: cosine similarity (CS, sentence embeddings were obtained using SBERT), word overlap (WO) and BLEU
Language quality: perplexity (PPL) using papuGaPT-2
Models were evaluated against two baselines:
Duplicate: a direct copy of the original text
Delete: letters of words recognized by Przetak as vulgar were replaced with asterisks (except for their the first letter)
Overall performance of the models was assessed using geometric mean of CS, STA and PPL scores.
Results
Method |
STA |
CS |
WO |
BLEU |
PPL |
GM |
Duplicate |
0.38 |
1.00 |
1.00 |
1.00 |
146.86 |
1.78 |
Delete |
1.00 |
0.93 |
0.84 |
0.92 |
246.80 |
4.14 |
GPT-2 |
0.90 |
0.86 |
0.71 |
0.86 |
258.44 |
3.71 |
GPT-3 |
0.88 |
0.92 |
0.79 |
0.92 |
359.12 |
3.58 |
T-5 base |
0.90 |
0.97 |
0.85 |
0.95 |
187.03 |
4.10 |
T-5 large |
0.93 |
0.97 |
0.86 |
0.95 |
170.02 |
4.31 |
Licence
CC-BY-NC 4.0
Citation
Klamra C., Wojdyga G. Żurowski S., Rosalska P., Kozłowska M., Ogrodniczuk M. (2022). Devulgarization of Polish Texts Using Pre-trained Language Models (in preparation).