--- title: "MorphoFiltered-Gemini at MWE-2026 PARSEME 2.0 — Moise 2026" description: "The paper describes MorphoFiltered-Gemini, a system entered in subtask 1 (MWE identification) of the PARSEME 2.0 shared task." authors: ["Irina Moise", "Sergiu Nisioi"] year: 2026 venue: "Proceedings of the 22nd Workshop on Multiword Expressions (MWE 2026)" source: "https://aclanthology.org/2026.mwe-1.26/" doi: "10.18653/v1/2026.mwe-1.26" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/papers/moise-2026-morphofiltered-gemini-mwe-2026-parseme/" --- [Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/moise-2026-morphofiltered-gemini-mwe-2026-parseme/) [home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2026](https://md.research.elamur.ai/free/papers/2026/page/3/) / MorphoFiltered-Gemini at MWE-2026 PARSEME 2.0 Subtask 1: Tackling LLM Overgeneration via Universal POS-based Constraints # MorphoFiltered-Gemini at MWE-2026 PARSEME 2.0 Subtask 1: Tackling LLM Overgeneration via Universal POS-based Constraints **Authors:** Irina Moise, [Sergiu Nisioi](https://md.research.elamur.ai/free/authors/sergiu-nisioi/) · **Year:** 2026 · **Venue:** Proceedings of the 22nd Workshop on Multiword Expressions (MWE 2026) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.mwe-1.26/) · [PDF](https://aclanthology.org/2026.mwe-1.26.pdf) · [DOI 10.18653/v1/2026.mwe-1.26](https://doi.org/10.18653/v1/2026.mwe-1.26) · [OpenAlex](https://openalex.org/W7140114746) **Citations:** 0 citations (openalex-snapshot · 2026-10-14) ## Summary The paper describes MorphoFiltered-Gemini, a system entered in subtask 1 (MWE identification) of the PARSEME 2.0 shared task. It covers all 17 languages, including Ukrainian, and all syntactic MWE types rather than only verbal ones. The authors address a known weakness of LLMs: they tag too many word combinations as multiword expressions. Their pipeline works as follows: - CUPT annotations are converted to BIO tags. - Gemini 2.0 Flash-Lite is prompted in batches, with separate prompts for span detection and for category labelling. - Few-shot examples from training data are used only for some languages. - A lightweight post-filter based on UD part-of-speech patterns discards implausible spans, such as DET+NOUN or ADJ+NOUN, and removes single-token predictions. Filters are enabled per language, depending on whether they improved development results. The system did not win on F1. However, it ranked third in token-based precision and had the most even performance across languages and categories of all submissions. This suggests that minimal, language-agnostic morphological constraints can make LLM-based MWE tagging more stable, which is useful for low-resource or typologically diverse languages. ## Key points - **Official scores:** MWE-based P/R/F1 was 20.95/14.50/17.14, and token-based P/R/F1 was 34.14/24.20/28.32. The system ranked third in token-based precision and had the top Shannon evenness score (0.97; entropy 3.71, richness 56.53). - **Filter coverage:** The POS-pattern filter was used for 11 languages, including UK. It was disabled for Hebrew, Japanese and Slovene, where it hurt results. The single-token filter was kept for EL, FA, GRC, KA and LV. - **Baselines tried:** A purely rule-based morphological baseline reached only 0.152 token F1. Using Gemini merely to validate those rule-based candidates brought almost no gain, because recall was too low to begin with. - **Seen vs. unseen MWEs:** Expressions seen in train/dev data scored F1 26.25 (P 75.06), while unseen ones scored only F1 8.89. This points to strong reliance on caching and memorization. - **Main limitation:** The BIO representation cannot encode discontinuous or overlapping MWEs, so discontinuous expressions scored zero. Remaining errors include missed split light-verb constructions and false positives on compositional patterns, such as Portuguese contractions. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [Linguistics & languages](https://md.research.elamur.ai/free/shelves/linguistics/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{moise2026morphofiltered, title = {{MorphoFiltered-Gemini at MWE-2026 PARSEME 2.0 Subtask 1: Tackling LLM Overgeneration via Universal POS-based Constraints}}, author = {Moise, Irina and Nisioi, Sergiu}, booktitle = {Proceedings of the 22nd Workshop on Multiword Expressions (MWE 2026)}, year = {2026}, doi = {10.18653/v1/2026.mwe-1.26}, url = {https://doi.org/10.18653/v1/2026.mwe-1.26} } ``` - [← previous Morphemes without Borders: Evaluating Root–Pattern Morphology in Arabic Tokenizers and LLMs](https://md.research.elamur.ai/free/papers/lingbulk-2026-alakeel-morphemes-without-borders-evaluating-root/) - [next → MORQA: Benchmarking Evaluation Metrics for Medical Open-Ended Question Answering](https://md.research.elamur.ai/free/papers/yim-2026-morqa-benchmarking-evaluation-metrics-medical/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/papers/2026/page/3/) ## References 2 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Timothy Baldwin and Su Nam Kim. 2010. Multiword Expressions. Taylor and Francis. [find](https://scholar.google.com/scholar?q=Timothy+Baldwin+and+Su+Nam+Kim%2E+2010%2E+Multiword+Expressions%2E+Taylor+and+Francis%2E) 2. Task: Extract multiword expressions (MWEs) from sentences in {lang_info[’name’]}. [find](https://scholar.google.com/scholar?q=Task%3A+Extract+multiword+expressions+%28MWEs%29+from+sentences+in+%7Blang%5Finfo%5B%E2%80%99name%E2%80%99%5D%7D%2E)