Peter Brusilovsky

6 papers · 2017–2025 · 3 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (15) 🌍 Conference Polyglot (3) 🏃 Academic Marathon (8) 🌈 Renaissance Researcher (5) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (14) 🧭 Keyword Pioneer 🏆 Keyword Champion (3) ❓ The Questioner

Conferences

ACL (3) EMNLP (2) NAACL (1)

Top co-authors

Jan Cegin (4) Jakub Simko (4) Daqing He (2) Maria Bielikova (2) Ivan Srba (2) Branislav Pecher (2) Rui Meng (2) Adam Trischler (1) Tong Wang (1) Sanqiang Zhao (1)

Keywords

text augmentation (3) data augmentation (3) large language model (3) keyphrase generation (2) intent classification (1) paraphrase generation (1) semantic meaning (1) generative model (1) recurrent neural network (1) sample selection (1) low-resource setting (1) encoder-decoder framework (1) lexical diversity (1) generation diversity (1) absent keyphrase (1) cost-benefit analysis (1) downstream model (1) diversity incentive (1) seq2seq keyphrase (1) variable number generation (1)

Papers

Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation EMNLP 2025

LLMs vs Established Text Augmentation Techniques for Classification: When do the Benefits Outweight the Costs? NAACL 2025

Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation ACL 2024

ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness EMNLP 2023

One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrases ACL 2020

Deep Keyphrase Generation ACL 2017