Papers by Pavel Braslavski
KazQAD: Kazakh Open-Domain Question Answering Dataset (2024.lrec-main)
Copied to clipboard
| Challenge: | KazQAD contains just under 6,000 unique questions with extracted short answers and nearly 12,000 passage-level relevance judgements. |
| Approach: | They introduce a Kazakh open-domain question answering dataset that can be used in reading comprehension and full ODQA settings. |
| Outcome: | The proposed dataset can be used in reading comprehension and full ODQA settings, as well as for information retrieval experiments. |
Large Dataset and Language Model Fun-Tuning for Humor Recognition (P19-1)
Copied to clipboard
| Challenge: | Humor recognition datasets contain only English texts and focus on puns. |
| Approach: | They collected a dataset of jokes and funny dialogues in Russian and complemented them carefully with unfunny texts with similar lexical properties. |
| Outcome: | The proposed method is based on the universal language model finetuning and has an F1 score of 0.91 on a test set. |
Entity Linking over Nested Named Entities for Russian (2022.lrec-1)
Copied to clipboard
Natalia Loukachevitch, Pavel Braslavski, Vladimir Ivanov, Tatiana Batura, Suresh Manandhar, Artem Shelmanov, Elena Tutubalina
| Challenge: | Entity linking is a popular NLP task, where a system needs to link a named entity to a concept in a knowledge base such as Wikidata. |
| Approach: | They describe the main design principles behind entity linking annotation in the recently released Russian NEREL dataset for information extraction. |
| Outcome: | The NEREL dataset is the largest Russian dataset annotated with entities and relations. |
You Told Me That Joke Twice: A Systematic Investigation of Transferability and Robustness of Humor Detection Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | a recent study shows that there is little research on how models trained on humor datasets generalize and behave in the wild. |
| Approach: | They analyze existing English humor datasets and train RoBERTa-based and Nave Bayes classifiers on them. |
| Outcome: | The proposed models show that they can generalize and behave on humor datasets, but the transferability of the models is poor. |
How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM? (2025.findings-naacl)
Copied to clipboard
Sergey Pletenev, Maria Marina, Daniil Moskovskiy, Vasily Konovalov, Pavel Braslavski, Alexander Panchenko, Mikhail Salnikov
| Challenge: | Low-rank adaptation (LoRA) is a popular training technique for updating or domain-specific adaptation of Large Language Models (LLMs). |
| Approach: | They propose to use low-rank adaptation to incorporate new facts into the LLM without compromising previously learned knowledge. |
| Outcome: | The proposed approach is harmful because the model's performance declines after such fine-tuning. |
A System for Answering Simple Questions in Multiple Languages (2023.acl-demo)
Copied to clipboard
| Challenge: | Existing knowledge graph question answering systems are limited to simple questions, but they can be used to answer complex questions. |
| Approach: | They propose a multilingual Knowledge Graph Question Answering technique that orders potential responses based on the distance between the question’s text embeddings and the answer’s graph embedds. |
| Outcome: | The proposed method consistently outperforms baseline systems, including seq2seq QA models and complex rule-based pipelines. |
CausalQA: A Benchmark for Causal Question Answering (2022.coling-1)
Copied to clipboard
Alexander Bondarenko, Magdalena Wolska, Stefan Heindorf, Lukas Blübaum, Axel-Cyrille Ngonga Ngomo, Benno Stein, Pavel Braslavski, Matthias Hagen, Martin Potthast
| Challenge: | Existing causal question answering datasets are relatively small and only include one type of causal question. |
| Approach: | They construct a benchmark corpus of 1.1 million causal questions with answers . they use a typology derived from a data-driven, manual analysis of QA datasets . |
| Outcome: | The proposed model achieves a ROUGE-L F1 score of 0.48 on the new QA benchmark. |