Improving the performance of UDify with Linguistic Typology Knowledge

Research output: Chapter in Book or Conference Publication/ProceedingConference Publicationpeer-review

3 Citations (Scopus)

Abstract

UDify is the state-of-the-art language-agnostic dependency parser which is trained on a polyglot corpus of 75 languages. This multilingual modeling enables the model to generalize over unknown/lesser-known languages, thus leading to improved performance on low-resource languages. In this work we used linguistic typology knowledge available in URIEL database, to improve the cross-lingual transferring ability of UDify even further.

Original languageEnglish
Title of host publicationSIGTYP 2021 - 3rd Workshop on Research in Computational Typology and Multilingual NLP, Proceedings of the Workshop
EditorsEkaterina Vylomova, Elizabeth Salesky, Sabrina Mielke, Gabriella Lapesa, Ritesh Kumar, Harald Hammarstrom, Ivan Vulic, Anna Korhonen, Roi Reichart, Edoardo Maria Ponti, Ryan Cotterell
PublisherAssociation for Computational Linguistics (ACL)
Pages38-60
Number of pages23
ISBN (Electronic)9781954085343
Publication statusPublished - 2021
Event3rd Workshop on Research in Computational Typology and Multilingual NLP, SIGTYP 2021 - Virtual, Online
Duration: 10 Jun 2021 → …

Publication series

NameSIGTYP 2021 - 3rd Workshop on Research in Computational Typology and Multilingual NLP, Proceedings of the Workshop

Conference

Conference3rd Workshop on Research in Computational Typology and Multilingual NLP, SIGTYP 2021
CityVirtual, Online
Period10/06/21 → …

Fingerprint

Dive into the research topics of 'Improving the performance of UDify with Linguistic Typology Knowledge'. Together they form a unique fingerprint.

Cite this