paper-with-me

Papers

Text Detoxification using Large Pre-trained Neural Models

2021-09-18 · EMNLP 2021 11 · David Dale, Anton Voronov, Daryna Dementieva, Varvara Logacheva, Olga Kozlova, Nikita Semenov, Alexander Panchenko

We present two novel unsupervised methods for eliminating toxicity in text. Our first method combines two recent ideas: (1) guidance of the generation process with small style-conditional language models and (2) use of paraphrasing models to perform style transfer. We use a well-performing paraphraser guided by style-trained language models to keep the text content and remove toxicity. Our second method uses BERT to replace toxic words with their non-offensive synonyms. We make the method more flexible by enabling BERT to replace mask tokens with a variable number of words. Finally, we present the first large-scale comparative study of style transfer models on the task of toxicity removal. We compare our models with a number of methods for style transfer. The models are evaluated in a reference-free way using a combination of unsupervised style transfer metrics. Both methods we suggest yield new SOTA results.

📄 PDF Abstract BibTeX arXiv:2109.08914

Code (1)

skoltech-nlp/detox 공식 구현 pytorch

Tasks

Style Transfer

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Weight Decay 설명 없음
WordPiece 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Similar Papers 제목 키워드 기반

Exploring Cross-lingual Text Detoxification with Large Multilingual Language Models.

2022-05-01 · ACL 2022 5 · Daniil Moskovskiy, Daryna Dementieva, Alexander Panchenko

Detoxification is a task of generating text in polite style while preserving meaning and fluency of the original toxic text. Existing detoxification methods are monolingual i.e. designed to work in one exact language. Th…

Style Transfer

Exploring Methods for Cross-lingual Text Style Transfer: The Case of Text Detoxification

2023-11-23 · Daryna Dementieva, Daniil Moskovskiy, David Dale, Alexander Panchenko

Text detoxification is the task of transferring the style of text from toxic to neutral. While here are approaches yielding promising results in monolingual setup, e.g., (Dale et al., 2021; Hallinan et al., 2022), cross-…

Cross-Lingual TransferStyle TransferText Style Transfer

Exploring Cross-lingual Textual Style Transfer with Large Multilingual Language Models

2022-06-05 · Daniil Moskovskiy, Daryna Dementieva, Alexander Panchenko

Detoxification is a task of generating text in polite style while preserving meaning and fluency of the original toxic text. Existing detoxification methods are designed to work in one exact language. This work investiga…

Style Transfer

DSCD: Large Language Model Detoxification with Self-Constrained Decoding

2025-10-15 · Ming Dong, Jinkui Zhang, Bolong Zheng, Xinhui Tu 외 arxiv

Detoxification in large language models (LLMs) remains a significant research challenge. Existing decoding detoxification methods are all based on external constraints, which require additional resource overhead and lose…

MultiParaDetox: Extending Text Detoxification with Parallel Data to New Languages

2024-04-02 · Daryna Dementieva, Nikolay Babakov, Alexander Panchenko

Text detoxification is a textual style transfer (TST) task where a text is paraphrased from a toxic surface form, e.g. featuring rude words, to the neutral register. Recently, text detoxification methods found their appl…

Style Transfer