Gleb Kuzmin


2023

pdf bib
Hybrid Uncertainty Quantification for Selective Text Classification in Ambiguous Tasks
Artem Vazhentsev | Gleb Kuzmin | Akim Tsvigun | Alexander Panchenko | Maxim Panov | Mikhail Burtsev | Artem Shelmanov
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Many text classification tasks are inherently ambiguous, which results in automatic systems having a high risk of making mistakes, in spite of using advanced machine learning models. For example, toxicity detection in user-generated content is a subjective task, and notions of toxicity can be annotated according to a variety of definitions that can be in conflict with one another. Instead of relying solely on automatic solutions, moderation of the most difficult and ambiguous cases can be delegated to human workers. Potential mistakes in automated classification can be identified by using uncertainty estimation (UE) techniques. Although UE is a rapidly growing field within natural language processing, we find that state-of-the-art UE methods estimate only epistemic uncertainty and show poor performance, or under-perform trivial methods for ambiguous tasks such as toxicity detection. We argue that in order to create robust uncertainty estimation methods for ambiguous tasks it is necessary to account also for aleatoric uncertainty. In this paper, we propose a new uncertainty estimation method that combines epistemic and aleatoric UE methods. We show that by using our hybrid method, we can outperform state-of-the-art UE methods for toxicity detection and other ambiguous text classification tasks.

pdf bib
Uncertainty Estimation for Debiased Models: Does Fairness Hurt Reliability?
Gleb Kuzmin | Artem Vazhentsev | Artem Shelmanov | Xudong Han | Simon Suster | Maxim Panov | Alexander Panchenko | Timothy Baldwin
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)

2022

pdf bib
Uncertainty Estimation of Transformer Predictions for Misclassification Detection
Artem Vazhentsev | Gleb Kuzmin | Artem Shelmanov | Akim Tsvigun | Evgenii Tsymbalov | Kirill Fedyanin | Maxim Panov | Alexander Panchenko | Gleb Gusev | Mikhail Burtsev | Manvel Avetisian | Leonid Zhukov
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Uncertainty estimation (UE) of model predictions is a crucial step for a variety of tasks such as active learning, misclassification detection, adversarial attack detection, out-of-distribution detection, etc. Most of the works on modeling the uncertainty of deep neural networks evaluate these methods on image classification tasks. Little attention has been paid to UE in natural language processing. To fill this gap, we perform a vast empirical investigation of state-of-the-art UE methods for Transformer models on misclassification detection in named entity recognition and text classification tasks and propose two computationally efficient modifications, one of which approaches or even outperforms computationally intensive methods.

pdf bib
ALToolbox: A Set of Tools for Active Learning Annotation of Natural Language Texts
Akim Tsvigun | Leonid Sanochkin | Daniil Larionov | Gleb Kuzmin | Artem Vazhentsev | Ivan Lazichny | Nikita Khromov | Danil Kireev | Aleksandr Rubashevskii | Olga Shahmatova | Dmitry V. Dylov | Igor Galitskiy | Artem Shelmanov
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

We present ALToolbox – an open-source framework for active learning (AL) annotation in natural language processing. Currently, the framework supports text classification, sequence tagging, and seq2seq tasks. Besides state-of-the-art query strategies, ALToolbox provides a set of tools that help to reduce computational overhead and duration of AL iterations and increase annotated data reusability. The framework aims to support data scientists and researchers by providing an easy-to-deploy GUI annotation tool directly in the Jupyter IDE and an extensible benchmark for novel AL methods. We prepare a small demonstration of ALToolbox capabilities available online. The code of the framework is published under the MIT license.

pdf bib
Towards Computationally Feasible Deep Active Learning
Akim Tsvigun | Artem Shelmanov | Gleb Kuzmin | Leonid Sanochkin | Daniil Larionov | Gleb Gusev | Manvel Avetisian | Leonid Zhukov
Findings of the Association for Computational Linguistics: NAACL 2022

Active learning (AL) is a prominent technique for reducing the annotation effort required for training machine learning models. Deep learning offers a solution for several essential obstacles to deploying AL in practice but introduces many others. One of such problems is the excessive computational resources required to train an acquisition model and estimate its uncertainty on instances in the unlabeled pool. We propose two techniques that tackle this issue for text classification and tagging tasks, offering a substantial reduction of AL iteration duration and the computational overhead introduced by deep acquisition models in AL. We also demonstrate that our algorithm that leverages pseudo-labeling and distilled models overcomes one of the essential obstacles revealed previously in the literature. Namely, it was shown that due to differences between an acquisition model used to select instances during AL and a successor model trained on the labeled data, the benefits of AL can diminish. We show that our algorithm, despite using a smaller and faster acquisition model, is capable of training a more expressive successor model with higher performance.

2020

pdf bib
Fake news detection for the Russian language
Gleb Kuzmin | Daniil Larionov | Dina Pisarevskaya | Ivan Smirnov
Proceedings of the 3rd International Workshop on Rumours and Deception in Social Media (RDSM)

In this paper, we trained and compared different models for fake news detection in Russian. For this task, we used such language features as bag-of-n-grams and bag of Rhetorical Structure Theory features, and BERT embeddings. We also compared the score of our models with the human score on this task and showed that our models deal with fake news detection better. We investigated the nature of fake news by dividing it into two non-overlapping classes: satire and fake news. As a result, we obtained the set of models for fake news detection; the best of these models achieved 0.889 F1-score on the test set for 2 classes and 0.9076 F1-score on 3 classes task.