Flexing in 73 Languages: A Single Small Model for Multilingual Inflection

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A10511655" target="_blank" >RIV/00216208:11320/25:10511655 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-032-02551-7_5" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-032-02551-7_5</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-032-02551-7_5" target="_blank" >10.1007/978-3-032-02551-7_5</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Flexing in 73 Languages: A Single Small Model for Multilingual Inflection

Popis výsledku v původním jazyce

We present a compact, single-model approach to multilingual inflection, the task of generating inflected word forms from base lemmas to express grammatical categories. Our model, trained jointly on data from 73 languages, is lightweight, robust to unseen words, and outperforms monolingual baselines in most languages. This demonstrates the effectiveness of multilingual modeling for inflection and highlights its practical benefits: simplifying deployment by eliminating the need to manage and retrain dozens of separate monolingual models. In addition to the standard SIGMORPHON shared task benchmarks, we evaluate our monolingual and multilingual models on 73 Universal Dependencies (UD) treebanks, extracting lemma-tag-form triples and their frequency counts. To ensure realistic data splits, we introduce a novel frequency-weighted, lemma-disjoint train-dev-test resampling procedure. Our work addresses the lack of an open-source, general-purpose, multilingual morphological inflection system capable of handli

Název v anglickém jazyce

Flexing in 73 Languages: A Single Small Model for Multilingual Inflection

Popis výsledku anglicky

We present a compact, single-model approach to multilingual inflection, the task of generating inflected word forms from base lemmas to express grammatical categories. Our model, trained jointly on data from 73 languages, is lightweight, robust to unseen words, and outperforms monolingual baselines in most languages. This demonstrates the effectiveness of multilingual modeling for inflection and highlights its practical benefits: simplifying deployment by eliminating the need to manage and retrain dozens of separate monolingual models. In addition to the standard SIGMORPHON shared task benchmarks, we evaluate our monolingual and multilingual models on 73 Universal Dependencies (UD) treebanks, extracting lemma-tag-form triples and their frequency counts. To ensure realistic data splits, we introduce a novel frequency-weighted, lemma-disjoint train-dev-test resampling procedure. Our work addresses the lack of an open-source, general-purpose, multilingual morphological inflection system capable of handli

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/EH22_008%2F0004605" target="_blank" >EH22_008/0004605: Přírodní a antropogenní georizika</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

28th International Conference on Text, Speech and Dialogue (Part II)

ISBN

978-3-032-02551-7

ISSN

—

e-ISSN

—

Počet stran výsledku

12

Strana od-do

39-50

Název nakladatele

Springer

Místo vydání

Cham, Switzerland

Místo konání akce

Erlangen, Germany

Datum konání akce

25. 8. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001576349100004