All

What are you looking for?

All
Projects
Results
Organizations

Quick search

  • Projects supported by TA ČR
  • Excellent projects
  • Projects with the highest public support
  • Current projects

Smart search

  • That is how I find a specific +word
  • That is how I leave the -word out of the results
  • “That is how I can find the whole phrase”

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

The result's identifiers

  • Result code in 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>

  • Result on the web

    <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>

Alternative languages

  • Result language

    angličtina

  • Original language name

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

  • Original language description

    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

  • Czech name

  • Czech description

Classification

  • Type

    D - Article in proceedings

  • CEP classification

  • OECD FORD branch

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

Result continuities

  • Project

    <a href="/en/project/EH22_008%2F0004605" target="_blank" >EH22_008/0004605: Natural and anthropogenic georisks</a><br>

  • Continuities

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

Others

  • Publication year

    2025

  • Confidentiality

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

Data specific for result type

  • Article name in the collection

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

  • ISBN

    978-3-032-02551-7

  • ISSN

  • e-ISSN

  • Number of pages

    12

  • Pages from-to

    39-50

  • Publisher name

    Springer

  • Place of publication

    Cham, Switzerland

  • Event location

    Erlangen, Germany

  • Event date

    Aug 25, 2025

  • Type of event by nationality

    WRD - Celosvětová akce

  • UT code for WoS article

    001576349100004