What has LeBenchmark Learnt about French Syntax?
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A4CHAY9HQ" target="_blank" >RIV/00216208:11320/25:4CHAY9HQ - isvavai.cz</a>
Result on the web
<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85195984103&partnerID=40&md5=dca83ca853a55ca15227c360045bc677" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85195984103&partnerID=40&md5=dca83ca853a55ca15227c360045bc677</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
What has LeBenchmark Learnt about French Syntax?
Original language description
The paper reports on a series of experiments aiming at probing LeBenchmark, a pretrained acoustic model trained on 7k hours of spoken French, for syntactic information. Pretrained acoustic models are increasingly used for downstream speech tasks such as automatic speech recognition, speech translation, spoken language understanding or speech parsing. They are trained on very low level information (the raw speech signal), and do not have explicit lexical knowledge. Despite that, they obtained reasonable results on tasks that requires higher level linguistic knowledge. As a result, an emerging question is whether these models encode syntactic information. We probe each representation layer of LeBenchmark for syntax, using the Orféo treebank, and observe that it has learnt some syntactic information. Our results show that syntactic information is more easily extractable from the middle layers of the network, after which a very sharp decrease is observed. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.
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
—
Continuities
—
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Jt. Int. Conf. Comput. Linguist., Lang. Resour. Eval., LREC-COLING - Main Conf. Proc.
ISBN
978-249381410-4
ISSN
—
e-ISSN
—
Number of pages
7
Pages from-to
17493-17499
Publisher name
European Language Resources Association (ELRA)
Place of publication
—
Event location
Torino, Italia
Event date
Jan 1, 2025
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—