Lemmatization of Polish Multi-word Expressions
Magdalena Król, Aleksander Smywinski-Pohl, Zbigniew Kaleta, Pawel Lewkowicz
Abstract
This paper explores the lemmatization of multi-word expressions (MWEs) and proper names in Polish -tasks complicated by linguistic irregularities and historical factors. Instead of using rule-based methods, we apply a machine learning approach with fine-tuned plT5 and mT5 models. We trained and validated the models on enhanced gold-standard data from the 2019 Pol-Eval task and evaluated the impact of additional fine-tuning on a silver-standard dataset derived from Wikipedia. Two setups were tested: one without context, and one using leftside context of the target MWE. Our best model achieved 86.23% AccCS (Accuracy Case-Sensitive), 89.43% AccCI (Accuracy Case-Insensitive), and a combined score of 88.79%, setting a new state-of-the-art for Polish MWE and named entity lemmatization, as confirmed by the PolEval maintainers. We also evaluated optimization and quantization techniques to reduce model size and inference time with modest quality loss.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on1
Related papers
- PL-MTEB: Polish Massive Text Embedding BenchmarkRafal Poswiata, Slawomir Dadas, Michal Wiktor PerelkiewiczACL Findings 2026
- MWE as WSD: Solving Multiword Expression Identification with Word Sense DisambiguationJoshua Tanner, Jacob HoffmanEMNLP Findings 2023 · 3 citations
- KLEJ: Comprehensive Benchmark for Polish Language UnderstandingPiotr Rybak, Robert Mroczkowski, Janusz Tracz, Ireneusz GawlikACL 2020 · 4 citations
- Lemma Dilemma: On Lemma Generation Without Domain- or Language-Specific Training DataOlia Toporkov, Alan Akbik, Rodrigo AgerriEMNLP Findings 2025 · 1 citation
- SlovakBERT: Slovak Masked Language ModelMatús Pikuliak, Stefan Grivalsky, Martin Konopka, Miroslav Blsták et al.EMNLP Findings 2022 · 32 citations
