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

## TL;DR

This paper introduces a new neural network model that jointly performs POS tagging and dependency parsing, leveraging shared features from bidirectional LSTMs, and achieves state-of-the-art results across 19 languages.

## Contribution

The novel model effectively combines POS tagging and dependency parsing using shared bidirectional LSTM features, surpassing previous neural network approaches.

## Key findings

- Outperforms existing models on 19 languages
- Achieves new state-of-the-art accuracy
- Open-source code and pre-trained models available

## 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