Olga Kozlova

4 papers · 2021–2021 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12) 🐣 Hot Topic Early Bird

Venues

EACL (2) EMNLP (1) SemEval (1)

Top co-authors

Alexander Panchenko (4) Varvara Logacheva (3) Nikita Semenov (3) David Dale (2) Dmitry V. Dylov (1) Nikita Khromov (1) Daryna Dementieva (1) Ekaterina Artemova (1) Artem Shelmanov (1) Denis Belyakov (1)

Research topics

Machine Learning (3) Natural Language Processing (3) Artificial Intelligence (2) Core Methods (2) Deep Learning (1) Application Areas (1) Applications (1) Core AI (1) Generation (1) Learning Paradigms (1) Learning Types (1) Optimization & Theory (1) Techniques (1) Understanding (1)

Keywords

sequence tagging (2) binary classification (1) transfer learning (1) bayesian inference (1) text classification (1) style transfer (1) model distillation (1) language model (1) toxicity classification (1) uncertainty estimation (1) pre-trained language model (1) text detoxification (1) monte carlo dropout (1) toxic span detection (1) transformer model (1) bayesian uncertainty (1) inappropriate message detection (1) topic-sensitive classification (1) reputation harm detection (1) active learning (1)

Papers

Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates EACL 2021 Detecting Inappropriate Messages on Sensitive Topics that Could Harm a Company’s Reputation EACL 2021 SkoltechNLP at SemEval-2021 Task 5: Leveraging Sentence-level Pre-training for Toxic Span Detection SemEval 2021 Text Detoxification using Large Pre-trained Neural Models EMNLP 2021