Probing Cross-lingual Transfer of XLM Multi-language Model
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3AR43F6RNZ" target="_blank" >RIV/00216208:11320/25:R43F6RNZ - isvavai.cz</a>
Result on the web
<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85186474840&doi=10.1007%2f978-3-031-53555-0_21&partnerID=40&md5=2dd368fbe6cc5fc20da4886433d53fc6" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85186474840&doi=10.1007%2f978-3-031-53555-0_21&partnerID=40&md5=2dd368fbe6cc5fc20da4886433d53fc6</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-031-53555-0_21" target="_blank" >10.1007/978-3-031-53555-0_21</a>
Alternative languages
Result language
angličtina
Original language name
Probing Cross-lingual Transfer of XLM Multi-language Model
Original language description
This paper investigates the ability of XLM language model to transfer linguistic knowledge cross-lingually, verifying if and to which extent syntactic dependency relationships learnt in a language are maintained in other languages. In detail, a structural probe is developed to analyse the cross-lingual syntactic transfer capability of XLM model and comparison of cross-language syntactic transfer among languages belonging to different families from a typological classification, which are characterised by very different syntactic constructions. The probe aims to reconstruct the dependency parse tree of a sentence in order to representing the input sentences with the contextual embeddings from XLM layers. The results of the experimental assessment improved the previous results obtained using mBERT model. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
Czech name
—
Czech description
—
Classification
Type
C - Chapter in a specialist book
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
—
Continuities
—
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Book/collection name
Advances in Internet, Data & Web Technologies
ISBN
978-3-031-53554-3
Number of pages of the result
10
Pages from-to
219-228
Number of pages of the book
462
Publisher name
Springer Science and Business Media Deutschland GmbH
Place of publication
—
UT code for WoS chapter
—