|
Size: 3584
Comment:
|
Size: 3584
Comment:
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 8: | Line 8: |
| === Download link === | === Download link === |
| Line 10: | Line 10: |
| * [[Archive|https://drive.google.com/file/d/1aG_zhzJCXikv8_dkppLu_rE48CqJC2pQ/view?usp=sharing]] (4.1 GB) | * [[https://drive.google.com/file/d/1aG_zhzJCXikv8_dkppLu_rE48CqJC2pQ/view?usp=sharing|Archive]] (4.1 GB) |
| Line 16: | Line 16: |
| * `data/evaluation_corpus.txt` – the corpus used to evaluate the models, originally published by [[Grochowski (2008)|https://ksiegarnia.pwn.pl/Slownik-polskich-przeklenstw-i-wulgaryzmow,917947408,p.html]]. | * `data/evaluation_corpus.txt` – the corpus used to evaluate the models, originally published by [[https://ksiegarnia.pwn.pl/Slownik-polskich-przeklenstw-i-wulgaryzmow,917947408,p.html|Grochowski (2008)]]. |
| Line 29: | Line 29: |
| Additionally, in order to run evaluation scripts, please install [[Przetak|https://github.com/MarcinCiura/przetak]] and update the value of the `GOPATH` variable in `evaluation/__init__.py` file. | Additionally, in order to run evaluation scripts, please install [[https://github.com/MarcinCiura/przetak|Przetak]] and update the value of the `GOPATH` variable in `evaluation/__init__.py` file. |
| Line 48: | Line 48: |
| * **Preservation of the content**: cosine similarity (CS, sentence embeddings were obtained using [SBERT](https://www.sbert.net)), word overlap (WO) and BLEU | * **Preservation of the content**: cosine similarity (CS, sentence embeddings were obtained using [[https://www.sbert.net|SBERT]]), word overlap (WO) and BLEU |
| Line 50: | Line 50: |
| [[papuGaPT-2|https://huggingface.co/flax-community/papuGaPT2]] | [[https://huggingface.co/flax-community/papuGaPT2|papuGaPT-2]] |
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 https://github.com/MarcinCiura/przetak * **Preservation of the content**: cosine similarity (CS, sentence embeddings were obtained using SBERT), word overlap (WO) and BLEU * **Language quality**: perplexity (PPL) 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 |
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 |
Licence
CC-BY 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).