← Back to papers
2018 COLING COLING 2018

VarIDE at PARSEME Shared Task 2018: Are Variants Really as Alike as Two Peas in a Pod?

Abstract

AbstractWe describe the VarIDE system (standing for Variant IDEntification) which participated in the edition 1.1 of the PARSEME shared task on automatic identification of verbal multiword expressions (VMWEs). Our system focuses on the task of VMWE variant identification by using morphosyntactic information in the training data to predict if candidates extracted from the test corpus could be idiomatic, thanks to a naive Bayes classifier. We report results for 19 languages.

❓ The Questioner
🌉 Interdisciplinary Bridge — Machine Learning and Natural Language Processing
🧭 Keyword Pioneer — morphosyntactic information
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Machine Learning, Mathematics & Optimization, Natural Language Processing

Authors

Caroline Pasquer , Carlos Ramisch , Agata Savary , Jean-Yves Antoine

Topics

Machine Learning > Core Methods > Classification Natural Language Processing > Understanding > Parsing

Keywords

naive bayes classifier verbal multiword expression morphosyntactic information variant identification
Download PDF

Related papers

DialEdit: Annotations for Spoken Conversational Image Editing 2018
Downward Compatible Revision of Dialogue Annotation 2018
Zero Pronoun Resolution with Attention-based Neural Network 2018
Triad-based Neural Network for Coreference Resolution 2018
Challenges of language technologies for the indigenous languages of the Americas 2018