Nothing Special   »   [go: up one dir, main page]

Civil Rephrases Of Toxic Texts With Self-Supervised Transformers

Léo Laugier, John Pavlopoulos, Jeffrey Sorensen, Lucas Dixon


Abstract
Platforms that support online commentary, from social networks to news sites, are increasingly leveraging machine learning to assist their moderation efforts. But this process does not typically provide feedback to the author that would help them contribute according to the community guidelines. This is prohibitively time-consuming for human moderators to do, and computational approaches are still nascent. This work focuses on models that can help suggest rephrasings of toxic comments in a more civil manner. Inspired by recent progress in unpaired sequence-to-sequence tasks, a self-supervised learning model is introduced, called CAE-T5. CAE-T5 employs a pre-trained text-to-text transformer, which is fine tuned with a denoising and cyclic auto-encoder loss. Experimenting with the largest toxicity detection dataset to date (Civil Comments) our model generates sentences that are more fluent and better at preserving the initial content compared to earlier text style transfer systems which we compare with using several scoring systems and human evaluation.
Anthology ID:
2021.eacl-main.124
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1442–1461
Language:
URL:
https://aclanthology.org/2021.eacl-main.124
DOI:
10.18653/v1/2021.eacl-main.124
Bibkey:
Cite (ACL):
Léo Laugier, John Pavlopoulos, Jeffrey Sorensen, and Lucas Dixon. 2021. Civil Rephrases Of Toxic Texts With Self-Supervised Transformers. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1442–1461, Online. Association for Computational Linguistics.
Cite (Informal):
Civil Rephrases Of Toxic Texts With Self-Supervised Transformers (Laugier et al., EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.124.pdf
Software:
 2021.eacl-main.124.Software.zip
Code
 LeoLaugier/conditional-auto-encoder-text-to-text-transfer-transformer
Data
Civil Comments