A Novel Neural Network Model for Joint POS Tagging and Graph-based Dependency Parsing

CONLL 2017  ·  Dat Quoc Nguyen, Mark Dras, Mark Johnson ·

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

PDF Abstract CONLL 2017 PDF CONLL 2017 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Part-Of-Speech Tagging UD Joint Bi-LSTM Avg accuracy 95.55 # 5

Methods


No methods listed for this paper. Add relevant methods here