Factual state discovery benchmark: evaluating fact elicitation in Polish tax law
M Bystroński, K Tagowski, DP Janiak, J Farganus, ŁM Augustyniak, T Kajdanowicz, …
ACL 2026
2026
Łukasz Augustyniak
Assistant
Łukasz is a Data Scientist with 8+ years of experience in various ML projects (social media monitoring, call center’s transcriptions analysis, recommendation engines, information extraction from texts, legal texts analysis, and many more). He is finishing a PhD in Machine Learning, related to aspect-based sentiment analysis at the Wroclaw University of Science and Technology, Poland. He received MSc in Computer Science from the Wroclaw University of Technology in 2013 with distinction. He also received an MA in Law from Wroclaw University in 2014, and he is still actively interested in the legal aspects of IT and analysis of legal documents using NLP.
Research interests
- Sentiment Analysis
- Information Extraction from Texts
- Legal Text Analysis
- Social Media Monitoring
- ASR Transcriptions Analysis
- Language Modeling
- Recommendation Engines
- IP Law
Research groups
Education
- 2013
MsC in Computer Science (excellent grade)
Wroclaw University of Science and Technology
- 2014
Master in Law
Wroclaw University
- 2015
Science - Management - Commercialization
Cambridge University, UK
- 0
PhD in Computer Science, Artificial Intelligence
Wroclaw University of Science and Technology
Publications27
Unseen influence: computational propaganda, free elections, and the reluctance to seek judicial remedies in Poland
ŁM Augustyniak, BM Kaczmarek-Templin, M Bernaczyk
Białostockie Studia Prawnicze = Białystok Legal Studies 30(4), 221–235
2025
Electoral agitation data set: the use case of the Polish election
M Baran, MA Wójcik, P Kolebski, K Rajda, ŁM Augustyniak, T Kajdanowicz, …
LREC 2022 32–36
2022
Massively Multilingual Corpus of Sentiment Datasets and Multi-faceted Sentiment Classification Benchmark
ŁM Augustyniak, S Woźniak, M Gruza, PŁ Gramacki, K Rajda, T Kajdanowicz, …
NeurIPS 2023 1–25
2023
Why aren’t we NER yet? Artifacts of ASR errors in named entity recognition in spontaneous speech transcript
P Szymański, ŁM Augustyniak, A Szymczak, M Morzy, K Surdyk, P Żelasko
Conference paper · Cited by 7
2023
This is the Way: Designing and Compiling LEPISZCZE, a Comprehensive NLP Benchmark for Polish
ŁM Augustyniak, K Tagowski, AK Sawczyn, DP Janiak, RD Bartusiak, A Szymczak, …, A Janz, P Szymański, T Kajdanowicz, M Piasecki, …
NeurIPS 2022 1–14
2022
Assessment of Massively Multilingual Sentiment Classifiers
K Rajda, Ł Augustyniak, P Gramacki, M Gruza, S Woźniak, T Kajdanowicz
Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis
2022
Fact-checking must go on!
J Binkowski, DP Janiak, AK Sawczyn, T Kajdanowicz, ŁM Augustyniak
Conference paper
2021
Fact-checking: relevance assessment of references in the Polish political domain
AK Sawczyn, J Binkowski, DP Janiak, ŁM Augustyniak, T Kajdanowicz
Knowledge-Based and Intelligent Information & Engineering Systems: Proceedings of the 25th International Conference KES 2021 1285–1293 · Cited by 4
2021
Comprehensive analysis of aspect term extraction methods using various text embeddings
ŁM Augustyniak, T Kajdanowicz, P Kazienko
Computer Speech and Language 69, 1–19 · Cited by 5
2021
Return on investment in machine learning: crossing the chasm between academia and business
ŁM Augustyniak, P Szymański, J Mizgajski, A Szymczak, M Morzy, P Żelasko
Foundations of Computing and Decision Sciences 45(4), 281–304 · Cited by 3
2020
WER we are and WER we think we are
P Szymański, ŁM Augustyniak, P Żelasko, M Morzy, A Szymczak, M Żyła-Hoppe, …
Findings of the Association for Computational Linguistics, Findings of ACL: EMNLP 2020, 16-20, November 3290–3295 · Cited by 1
2020
Punctuation prediction in spontaneous conversations: can we mitigate ASR errors with retrofitted word embeddings?
ŁM Augustyniak, P Szymański, M Morzy, P Żelasko, A Szymczak, J Mizgajski, …
Interspeech 2020 4906–4910 · Cited by 3
2020
Political advertising dataset: the use case of the Polish 2020 presidential elections
ŁM Augustyniak, K Rajda, T Kajdanowicz, M Bernaczyk
ACL 2020 110–114 · Cited by 5
2020
Avaya Conversational Intelligence: a real-time system for Spoken Language Understanding in human-human call center conversations
P Szymański, ŁM Augustyniak, J Mizgajski, A Szymczak, R Głowski, P Żelasko, …
International Speech Communication Association 3659–3660
2019
Aspect detection using word and char embeddings with (Bi)LSTM and CRF
ŁM Augustyniak, T Kajdanowicz, P Kazienko
2019 IEEE Second International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), 3-5 June 2019, Cagliari, Sardinia, Italy 43–50
2019
WordNet2Vec: corpora agnostic word vectorization method
RD Bartusiak, ŁM Augustyniak, T Kajdanowicz, P Kazienko, M Piasecki
Neurocomputing 326, 141–150 · Cited by 20
2019
Extracting aspects hierarchies using Rhetorical Structure Theory
ŁM Augustyniak, T Kajdanowicz, P Kazienko
ACAI 2018 1–5
2018
Method for aspect-based sentiment annotation using rhetorical analysis
ŁM Augustyniak, K Rajda, T Kajdanowicz
ACIIDS 2017 772–781 · Cited by 2
2017
Three is more interesting than two
WJ Tuligłowicz, ŁM Augustyniak, P Szymański, T Kajdanowicz
Conference paper
2016
Showing 20 of 27