This paper describes a semi-supervised system that jointly learns verbal multiword expressions (VMWEs) and dependency parse trees as an auxiliary task. The model benefits from pre-trained multilingual BERT. BERT hidden layers are shared among the two tasks and we introduce an additional linear layer to retrieve VMWE tags. The dependency parse tree prediction is modelled by a linear layer and a bilinear one plus a tree CRF on top of BERT. The system has participated in the open track of the PARSEME shared task 2020 and ranked first in terms of F1-score in identifying unseen VMWEs as well as VMWEs in general, averaged across all 14 languages.
|Publication status||Published - 2 Dec 2020|
|Event||MWE-LEX 2020: Joint Workshop on Multiword Expressions and Electronic Lexicons (co-located with COLING 2020) - Virtual|
Duration: 13 Dec 2020 → 13 Dec 2020
|Abbreviated title||MWE-LEX 2020|
|Period||13/12/20 → 13/12/20|