Papers by Katsiaryna Mirylenka
Investigating Active Learning Sampling Strategies for Extreme Multi Label Text Classification (2022.lrec-1)
Copied to clipboard
| Challenge: | Large scale, multi-label text datasets with high numbers of different classes are expensive to annotate due to domain experts taking a lot of time working through all the classes. |
| Approach: | They propose to build classifiers on multi-label text datasets using Active Learning to reduce labeling effort. |
| Outcome: | The proposed classifiers can be used to reduce labeling effort on multi-label datasets. |
Evaluating Pre-Trained Sentence-BERT with Class Embeddings in Active Learning for Multi-Label Text Classification (2022.aacl-short)
Copied to clipboard
| Challenge: | Existing Active Learning strategies for pre-trained transformer language models are limited and do not work well on domain-specific datasets. |
| Approach: | They employ pre-trained transformer sentence embeddings to group samples with the same labels in the embeddable space on a legal document corpus. |
| Outcome: | The proposed method performs significantly worse than baselines on two domain-specific datasets. |
Reinforced Active Learning for Low-Resource, Domain-Specific, Multi-Label Text Classification (2023.findings-acl)
Copied to clipboard
| Challenge: | Modern text classification systems achieve excellent accuracy across tasks and corpora. |
| Approach: | They propose a Reinforcement Learning policy that uses many different aspects of the data and task to select the most informative unlabeled subset dynamically over the course of the AL procedure. |
| Outcome: | The proposed framework outperforms baselines on four complex multi-class, multi-label text classification datasets. |
Adapting LLMs for Structured Natural Language API Integration (2024.emnlp-industry)
Copied to clipboard
Robin Chan, Katsiaryna Mirylenka, Thomas Gschwind, Christoph Miksovic, Paolo Scotton, Enrico Toniato, Abdel Labbi
| Challenge: | API integration is crucial for enterprise systems, but there are challenges in combining APIs based on user intent. |
| Approach: | They propose a framework that leverages large language models to integrate APIs based on natural language input. |
| Outcome: | The proposed framework improves performance over existing methods and RAGs based on open APIs . it can learn structural API constraints implicitly during training and retain structured knowledge . |