Daryna Dementieva


2023

pdf bib
Exploring Methods for Cross-lingual Text Style Transfer: The Case of Text Detoxification
Daryna Dementieva | Daniil Moskovskiy | David Dale | Alexander Panchenko
Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
IFAN: An Explainability-Focused Interaction Framework for Humans and NLP Models
Edoardo Mosca | Daryna Dementieva | Tohid Ebrahim Ajdari | Maximilian Kummeth | Kirill Gringauz | Yutong Zhou | Georg Groh
Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: System Demonstrations

pdf bib
Detecting Text Formality: A Study of Text Classification Approaches
Daryna Dementieva | Nikolay Babakov | Alexander Panchenko
Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing

Formality is one of the important characteristics of text documents. The automatic detection of the formality level of a text is potentially beneficial for various natural language processing tasks. Before, two large-scale datasets were introduced for multiple languages featuring formality annotation—GYAFC and X-FORMAL. However, they were primarily used for the training of style transfer models. At the same time, the detection of text formality on its own may also be a useful application. This work proposes the first to our knowledge systematic study of formality detection methods based on statistical, neural-based, and Transformer-based machine learning methods and delivers the best-performing models for public usage. We conducted three types of experiments – monolingual, multilingual, and cross-lingual. The study shows the overcome of Char BiLSTM model over Transformer-based ones for the monolingual and multilingual formality classification task, while Transformer-based classifiers are more stable to cross-lingual knowledge transfer.

pdf bib
Adam-Smith at SemEval-2023 Task 4: Discovering Human Values in Arguments with Ensembles of Transformer-based Models
Daniel Schroter | Daryna Dementieva | Georg Groh
Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)

This paper presents the best-performing approach alias “Adam Smith” for the SemEval-2023 Task 4: “Identification of Human Values behind Arguments”. The goal of the task was to create systems that automatically identify the values within textual arguments. We train transformer-based models until they reach their loss minimum or f1-score maximum. Ensembling the models by selecting one global decision threshold that maximizes the f1-score leads to the best-performing system in the competition. Ensembling based on stacking with logistic regressions shows the best performance on an additional dataset provided to evaluate the robustness (“Nahj al-Balagha”). Apart from outlining the submitted system, we demonstrate that the use of the large ensemble model is not necessary and that the system size can be significantly reduced.

pdf bib
AdamR at SemEval-2023 Task 10: Solving the Class Imbalance Problem in Sexism Detection with Ensemble Learning
Adam Rydelek | Daryna Dementieva | Georg Groh
Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)

The Explainable Detection of Online Sexism task presents the problem of explainable sexism detection through fine-grained categorisation of sexist cases with three subtasks. Our team experimented with different ways to combat class imbalance throughout the tasks using data augmentation and loss alteration techniques. We tackled the challenge by utilising ensembles of Transformer models trained on different datasets, which are tested to find the balance between performance and interpretability. This solution ranked us in the top 40% of teams for each of the tracks.

2022

pdf bib
A Study on Manual and Automatic Evaluation for Text Style Transfer: The Case of Detoxification
Varvara Logacheva | Daryna Dementieva | Irina Krotova | Alena Fenogenova | Irina Nikishina | Tatiana Shavrina | Alexander Panchenko
Proceedings of the 2nd Workshop on Human Evaluation of NLP Systems (HumEval)

It is often difficult to reliably evaluate models which generate text. Among them, text style transfer is a particularly difficult to evaluate, because its success depends on a number of parameters. We conduct an evaluation of a large number of models on a detoxification task. We explore the relations between the manual and automatic metrics and find that there is only weak correlation between them, which is dependent on the type of model which generated text. Automatic metrics tend to be less reliable for better-performing models. However, our findings suggest that, ChrF and BertScore metrics can be used as a proxy for human evaluation of text detoxification to some extent.

pdf bib
ParaDetox: Detoxification with Parallel Data
Varvara Logacheva | Daryna Dementieva | Sergey Ustyantsev | Daniil Moskovskiy | David Dale | Irina Krotova | Nikita Semenov | Alexander Panchenko
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We present a novel pipeline for the collection of parallel data for the detoxification task. We collect non-toxic paraphrases for over 10,000 English toxic sentences. We also show that this pipeline can be used to distill a large existing corpus of paraphrases to get toxic-neutral sentence pairs. We release two parallel corpora which can be used for the training of detoxification models. To the best of our knowledge, these are the first parallel datasets for this task. We describe our pipeline in detail to make it fast to set up for a new language or domain, thus contributing to faster and easier development of new parallel resources. We train several detoxification models on the collected data and compare them with several baselines and state-of-the-art unsupervised approaches. We conduct both automatic and manual evaluations. All models trained on parallel data outperform the state-of-the-art unsupervised models by a large margin. This suggests that our novel datasets can boost the performance of detoxification systems.

pdf bib
Exploring Cross-lingual Text Detoxification with Large Multilingual Language Models.
Daniil Moskovskiy | Daryna Dementieva | Alexander Panchenko
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop

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. This work investigates multilingual and cross-lingual detoxification and the behavior of large multilingual models in this setting. Unlike previous works we aim to make large language models able to perform detoxification without direct fine-tuning in a given language. Experiments show that multilingual models are capable of performing multilingual style transfer. However, tested state-of-the-art models are not able to perform cross-lingual detoxification and direct fine-tuning on exact language is currently inevitable and motivating the need of further research in this direction.

pdf bib
SkoltechNLP at SemEval-2022 Task 8: Multilingual News Article Similarity via Exploration of News Texts to Vector Representations
Mikhail Kuimov | Daryna Dementieva | Alexander Panchenko
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)

This paper describes our contribution to SemEval 2022 Task 8: Multilingual News Article Similarity. The aim was to test completely different approaches and distinguish the best performing. That is why we’ve considered systems based on Transformer-based encoders, NER-based, and NLI-based methods (and their combination with SVO dependency triplets representation). The results prove that Transformer models produce the best scores. However, there is space for research and approaches that give not yet comparable but more interpretable results.

2021

pdf bib
Text Detoxification using Large Pre-trained Neural Models
David Dale | Anton Voronov | Daryna Dementieva | Varvara Logacheva | Olga Kozlova | Nikita Semenov | Alexander Panchenko
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

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 bib
Cross-lingual Evidence Improves Monolingual Fake News Detection
Daryna Dementieva | Alexander Panchenko
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop

Misleading information spreads on the Internet at an incredible speed, which can lead to irreparable consequences in some cases. Therefore, it is becoming essential to develop fake news detection technologies. While substantial work has been done in this direction, one of the limitations of the current approaches is that these models are focused only on one language and do not use multilingual information. In this work, we propose a new technique based on cross-lingual evidence (CE) that can be used for fake news detection and improve existing approaches. The hypothesis of the usage of cross-lingual evidence as a feature for fake news detection is confirmed, firstly, by manual experiment based on a set of known true and fake news. Besides, we compared our fake news classification system based on the proposed feature with several strong baselines on two multi-domain datasets of general-topic news and one newly fake COVID-19 news dataset showing that combining cross-lingual evidence with strong baselines such as RoBERTa yields significant improvements in fake news detection.

2020

pdf bib
SkoltechNLP at SemEval-2020 Task 11: Exploring Unsupervised Text Augmentation for Propaganda Detection
Daryna Dementieva | Igor Markov | Alexander Panchenko
Proceedings of the Fourteenth Workshop on Semantic Evaluation

This paper presents a solution for the Span Identification (SI) task in the “Detection of Propaganda Techniques in News Articles” competition at SemEval-2020. The goal of the SI task is to identify specific fragments of each article which contain the use of at least one propaganda technique. This is a binary sequence tagging task. We tested several approaches finally selecting a fine-tuned BERT model as our baseline model. Our main contribution is an investigation of several unsupervised data augmentation techniques based on distributional semantics expanding the original small training dataset as applied to this BERT-based sequence tagger. We explore various expansion strategies and show that they can substantially shift the balance between precision and recall, while maintaining comparable levels of the F1 score.