RUSSE-2022: Findings of the First Russian Detoxification Shared Task Based on Parallel Corpora

Abstract

Text detoxification is the task of rewriting a toxic text into a neutral text while preserving its original content. It has a wide range of applications, e.g. moderation of output of neural chatbots or suggesting less emotional version of posts on social networks. This paper provides a description of RUSSE-2022 competition of detoxification methods for the Russian language. This is the first competition which features (i) parallel training data and (ii) manual evaluation. We describe the setup of the competition, the solutions of the participating teams and analyse their performance. In addition to that, the large-scale evaluation allows us to analyse the performance of automatic evaluation metrics.

Towards a Russian Multimedia Politeness Corpus

“…In a broader context, there have been works on speech strategies in interactions between interlocutors in situations of persuasion and provocation (Issers, 2009), functions of imperative verb forms in a situation of request or prompt (Paducheva, 2010), and extralinguistic conditions of spontaneous speech interactions (Zemskaja et al, 1981). Most of these studies describe qualitative traits of communication while quantitative studies have been confined to the tasks of automatic detection of speech aggression and detoxification of online communication (Dementieva et al, 2021;Dementieva et al, 2022). The aim of our project is to develop the annotation framework for oral communicative interaction that on one hand takes into account approaches from linguistic politeness theories and on the other could be used for qualitative research and the NLP applications.…”

Between Denoising and Translation: Experiments in Text Detoxification

“…The existing methods of text detoxification and style transfer are mostly made for the English language, which makes it difficult to transfer to other languages. For this purpose, the RUSSE Detoxification corpus (Dementieva et al, 2022) was developed to solve the detoxification problem in the Russian language. This paper describes the general problem statement and proposes a detoxification method based on RuT5 and describes in detail experiments with autoregressive (AR) and non-autoregressive models (NAR) for style transfer.…”

Prompt Tuning for Text Detoxification

“…That led to the domination of unsupervised approaches, such as . RUSSE Detox shared task (Dementieva et al, 2022) provides the first parallel detoxification dataset for Russian, which allows exploring the capabilities of generic text-to-text methods in application to the task. In this paper, we present a solution based on prompt tuning.…”