no code implementations • JEP/TALN/RECITAL 2022 • Marie Candito
L’analyseur biaffine de Dozat & Manning (2017), qui produit des arbres de dépendances syntaxiques, a été étendu avec succès aux graphes de dépendances syntaxico-sémantiques (Dozat & Manning, 2018).
no code implementations • WS (NoDaLiDa) 2019 • Hazem Al Saied, Marie Candito, Mathieu Constant
In this paper, we compare the use of linear versus neural classifiers in a greedy transition system for MWE identification.
no code implementations • WS (NoDaLiDa) 2019 • Silvio Ricardo Cordeiro, Marie Candito
This paper analyzes results on light-verb construction identification from the PARSEME shared-task, distinguishing between simple cases that could be directly learned from training data from more complex cases that require an extra level of semantic processing.
no code implementations • COLING (MWE) 2020 • Carlos Ramisch, Agata Savary, Bruno Guillaume, Jakub Waszczuk, Marie Candito, Ashwini Vaidya, Verginica Barbu Mititelu, Archna Bhatia, Uxoa Iñurrieta, Voula Giouli, Tunga Güngör, Menghan Jiang, Timm Lichte, Chaya Liebeskind, Johanna Monti, Renata Ramisch, Sara Stymne, Abigail Walsh, Hongzhi Xu
We present edition 1. 2 of the PARSEME shared task on identification of verbal multiword expressions (VMWEs).
no code implementations • 12 Feb 2024 • Anna Mosolova, Marie Candito, Carlos Ramisch
We also propose two new WiC test sets for which we show that our fine-tuning method achieves substantial improvements.
1 code implementation • Findings (ACL) 2022 • Marie Candito
The biaffine parser of Dozat and Manning (2017) was successfully extended to semantic dependency parsing (SDP) (Dozat and Manning, 2018).