Papers by Tomasz Kajdanowicz
Controversy and Conformity: from Generalized to Personalized Aggressiveness Detection (2021.acl-long)
Copied to clipboard
Kamil Kanclerz, Alicja Figas, Marcin Gruza, Tomasz Kajdanowicz, Jan Kocon, Daria Puchalska, Przemyslaw Kazienko
| Challenge: | a new method to personalize documents that are perceived differently by users is needed . a recent study found that only a few annotations of controversial documents outperform classic methods . |
| Approach: | They propose to use some known, most controversial texts whose offensiveness is very ambiguous . they use user conformity-based measures or embeddings of their previous annotations to improve personalized reasoning . |
| Outcome: | The proposed methods outperform standard methods in document controversy and user nonconformity . the more controversial the content, the greater the gain, the authors say . |
Empowering Small-Scale Knowledge Graphs: A Strategy of Leveraging General-Purpose Knowledge Graphs for Enriched Embeddings (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing approaches to augment LLMs with Knowledge Graphs (KGs) Knowledge-intensive tasks are prone to errors and require a large amount of knowledge to be understood. |
| Approach: | They propose a framework for augmenting LLMs through Knowledge Graphs (KGs) they propose KGs can be used to enhance performance in knowledge-intensive tasks . |
| Outcome: | Experimental results show that a small domain-specific KG can benefit from a performance boost in downstream tasks when linked to a substantial general-purpose KG. |
Domain-Agnostic Neural Architecture for Class Incremental Continual Learning in Document Processing Platform (2023.acl-industry)
Copied to clipboard
| Challenge: | Recent methods with stochastic gradient learning struggle in streaming data setups and are restricted to specific domains. |
| Approach: | They propose a fully differentiable architecture that enables the training of high-performance classifiers when examples from each class are presented separately. |
| Outcome: | The proposed architecture achieves SOTA results without a memory buffer and clearly outperforms the reference methods. |
Developing PUGG for Polish: A Modern Approach to KBQA, MRC, and IR Dataset Construction (2024.findings-acl)
Copied to clipboard
Albert Sawczyn, Katsiaryna Viarenich, Konrad Wojtasik, Aleksandra Domogała, Marcin Oleksy, Maciej Piasecki, Tomasz Kajdanowicz
| Challenge: | Existing KBQA datasets are outdated and inefficient in human labor, and assisting tools like Large Language Models (LLM) are not utilized to reduce the workload. |
| Approach: | They propose a semi-automated question answering task that uses structured knowledge graphs to answer extensive knowledge-intensive questions. |
| Outcome: | The proposed approach includes KBQA, MRC, and Information Retrieval tasks for low-resource languages. |