Samenvatting
This paper presents a comprehensive set of probing experiments using a multilingual language model, XLM-R, for temporal relation classification between events in four languages. Results show an advantage of contextualized embeddings over static ones and a detrimen- tal role of sentence level embeddings. While obtaining competitive results against state-of-the-art systems, our probes indicate a lack of suitable encoded information to properly address this task.
pdf bib abs
pdf bib abs
Originele taal-2 | English |
---|---|
Titel | Proceedings of the 29th International Conference on Computational Linguistics |
Plaats van productie | Gyeongju, Republic of Korea |
Uitgeverij | International Committee on Computational Linguistics (ICCL) |
Pagina's | 3197-3209 |
Aantal pagina's | 13 |
Status | Published - 2022 |
Evenement | 29th International Conference on Computational Linguistics - Gyeongju, Korea, Republic of Duur: 12-okt.-2022 → 17-okt.-2022 |
Conference
Conference | 29th International Conference on Computational Linguistics |
---|---|
Verkorte titel | COLING 2022 |
Land/Regio | Korea, Republic of |
Stad | Gyeongju |
Periode | 12/10/2022 → 17/10/2022 |
Vingerafdruk
Duik in de onderzoeksthema's van 'How About Time? Probing a Multilingual Language Model for Temporal Relations'. Samen vormen ze een unieke vingerafdruk.Prijzen
-
Outstanding Paper - COLING 2022
Caselli, T. (Recipient), Dini, I. (Recipient) & Dell'Orletta, F. (Recipient), 2022
Prijs: National/international honour › Academic