75 Languages, 1 Model: Parsing Universal Dependencies Universally
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10405574" target="_blank" >RIV/00216208:11320/19:10405574 - isvavai.cz</a>
Result on the web
<a href="https://www.aclweb.org/anthology/D19-1279/" target="_blank" >https://www.aclweb.org/anthology/D19-1279/</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.18653/v1/D19-1279" target="_blank" >10.18653/v1/D19-1279</a>
Alternative languages
Result language
angličtina
Original language name
75 Languages, 1 Model: Parsing Universal Dependencies Universally
Original language description
We present UDify, a multilingual multi-task model capable of accurately predicting universal part-of-speech, morphological features, lemmas, and dependency trees simultaneously for all 124 Universal Dependencies treebanks across 75 languages. By leveraging a multilingual BERT self-attention model pretrained on 104 languages, we found that fine-tuning it on all datasets concatenated together with simple softmax classifiers for each UD task can result in state-of-the-art UPOS, UFeats, Lemmas, UAS, and LAS scores, without requiring any recurrent or language-specific components. We evaluate UDify for multilingual learning, showing that low-resource languages benefit the most from cross-linguistic annotations. We also evaluate for zero-shot learning, with results suggesting that multilingual training provides strong UD predictions even for languages that neither UDify nor BERT have ever been trained on. Code for UDify is available at https://github.com/hyperparticle/udify.
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
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
ISBN
978-1-950737-90-1
ISSN
—
e-ISSN
—
Number of pages
17
Pages from-to
2779-2795
Publisher name
Association for Computational Linguistics
Place of publication
Stroudsburg, PA, USA
Event location
Hong Kong, China
Event date
Nov 3, 2019
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—