Skip to Main content Skip to Navigation
Conference papers

Phylogenetic Multi-Lingual Dependency Parsing

Mathieu Dehouck 1, 2 Pascal Denis 2
2 MAGNET - Machine Learning in Information Networks
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
Abstract : Languages evolve and diverge over time. Their evolutionary history is often depicted in the shape of a phylogenetic tree. Assuming parsing models are representations of their languages grammars, their evolution should follow a structure similar to that of the phylo-genetic tree. In this paper, drawing inspiration from multi-task learning, we make use of the phylogenetic tree to guide the learning of multilingual dependency parsers leverag-ing languages structural similarities. Experiments on data from the Universal Dependency project show that phylogenetic training is beneficial to low resourced languages and to well furnished languages families. As a side product of phylogenetic training, our model is able to perform zero-shot parsing of previously unseen languages.
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download
Contributor : Mathieu Dehouck <>
Submitted on : Wednesday, May 29, 2019 - 3:31:25 PM
Last modification on : Friday, December 11, 2020 - 6:44:07 PM


Files produced by the author(s)


  • HAL Id : hal-02143747, version 1


Mathieu Dehouck, Pascal Denis. Phylogenetic Multi-Lingual Dependency Parsing. NAACL 2019 - Annual Conference of the North American Chapter of the Association for Computational Linguistics, Jun 2019, Minneapolis, United States. ⟨hal-02143747⟩



Record views


Files downloads