A Novel Neural Network Model for Joint POS Tagging and Graph-based Dependency Parsing
Abstract
We present a novel neural network model that learns POS tagging and graph-based dependency parsing jointly. Our model uses bidirectional LSTMs to learn feature representations shared for both POS tagging and dependency parsing tasks, thus handling the feature-engineering problem. Our extensive experiments, on 19 languages from the Universal Dependencies project, show that our model outperforms the state-of-the-art neural network-based Stack-propagation model for joint POS tagging and transition-based dependency parsing, resulting in a new state of the art. Our code is open-source and available together with pre-trained models at: https://github.com/datquocnguyen/jPTDP
Cite
@article{arxiv.1705.05952,
title = {A Novel Neural Network Model for Joint POS Tagging and Graph-based Dependency Parsing},
author = {Dat Quoc Nguyen and Mark Dras and Mark Johnson},
journal= {arXiv preprint arXiv:1705.05952},
year = {2017}
}
Comments
v2: also include universal POS tagging, UAS and LAS accuracies w.r.t gold-standard segmentation on Universal Dependencies 2.0 - CoNLL 2017 shared task test data; in CoNLL 2017