mind-the-gap-py
Résumé
mind-the-gap-py is a transition-based discontinuous parser implemented in Python.
This is a notice for the following release: https://doi.org/10.5281/zenodo.4775955 that contain pretrained models for English and German (including bert-based) to replicate experiments in :
BERT-Proof Syntactic Structures: Investigating Errors in Discontinuous Constituency Parsing
Maximin Coavoux
Findings of ACL 2021
Domaines
Informatique et langage [cs.CL]
Cite hal-03339847v1 Objet présenté à une conférence Maximin Coavoux. BERT-Proof Syntactic Structures: Investigating Errors in Discontinuous Constituency Parsing. Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021), Association for Computational Linguistics, Aug 2021, Online, France. pp.3259-3272, ⟨10.18653/v1/2021.findings-acl.288⟩. ⟨hal-03339847⟩
