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 detrimental 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.
How About Time? Probing a Multilingual Language Model for Temporal Relations
-
2022
Abstract
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 detrimental 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.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.