2025
Attention on Multiword Expressions: A Multilingual Study of BERT-based Models with Regard to Idiomaticity and Microsyntax
NAACL 2025findings
This study analyzes the attention patterns of fine-tuned encoder-only models based on the BERT architecture (BERT-based models) towards two distinct types of Multiword Expressions (MWEs): idioms and microsyntactic units (MSUs). Idioms present challenges in semantic non-compositionality, whereas MSUs…