A Novel Neural Network Model for Joint POS Tagging and Graph-based Dependency Parsing (2017-05-16T00:00:00.000000Z)

TL;DR

A novel neural network model is presented that 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.

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

Authors

Mark Johnson

4 papers

Dat Quoc Nguyen

12 papers

M. Dras

3 papers

TL;DR

Abstract

Authors

References54 items

Universal Dependencies 2.0 – CoNLL 2017 Shared Task Development and Test Data

Deep Multitask Learning for Semantic Dependency Parsing

DyNet: The Dynamic Neural Network Toolkit

Neural Probabilistic Model for Non-projective MST Parsing

Deep Biaffine Attention for Neural Dependency Parsing

An empirical study for Vietnamese dependency parsing

Bi-directional Attention with Agreement for Dependency Parsing

Joint part-of-speech and dependency projection from multiple sources

Probabilistic Graph-based Dependency Parsing with Convolutional Neural Network

Graph-based Dependency Parsing with Bidirectional LSTM

UDPipe: Trainable Pipeline for Processing CoNLL-U Files Performing Tokenization, Morphological Analysis, POS Tagging and Parsing

Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss

Globally Normalized Transition-Based Neural Networks

Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations

Stack-propagation: Improved Representation Learning for Syntax

Easy-First Dependency Parsing with Hierarchical Tree LSTMs

A Primer on Neural Network Models for Natural Language Processing

Improved Transition-Based Parsing and Tagging with Neural Networks

Improved Transition-based Parsing by Modeling Characters instead of Words with LSTMs

An Effective Neural Network Model for Graph-based Dependency Parsing

Structured Training for Neural Network Transition-Based Parsing

Transition-Based Dependency Parsing with Stack Long Short-Term Memory

Universal Dependencies 1.4

Adam: A Method for Stochastic Optimization

Adapting taggers to Twitter with not-so-distant supervision

Joint POS Tagging and Transition-based Constituent Parsing in Chinese with Non-local Features

Low-Rank Tensors for Scoring Dependency Structures

Transition-based Dependency Parsing with Selectional Branching

Turning on the Turbo: Fast Third-Order Non-Projective Turbo Parsers

Joint Chinese Word Segmentation, POS Tagging and Parsing

A Transition-Based System for Joint Part-of-Speech Tagging and Labeled Non-Projective Dependency Parsing

Incremental Joint POS Tagging and Dependency Parsing in Chinese

Joint Models for Chinese POS Tagging and Dependency Parsing

A Discriminative Model for Joint Morphological Disambiguation and Dependency Parsing

Transition-based Dependency Parsing with Rich Non-local Features

A Universal Part-of-Speech Tagset

Analyzing and Integrating Dependency Parsers

Efficient Third-Order Dependency Parsers

The CoNLL 2007 Shared Task on Dependency Parsing

CoNLL-X Shared Task on Multilingual Dependency Parsing

Online Learning of Approximate Dependency Parsing Algorithms

Online Large-Margin Training of Dependency Parsers

Statistical Dependency Analysis with Support Vector Machines

TnT – A Statistical Part-of-Speech Tagger

Bidirectional recurrent neural networks

Long Short-Term Memory

Three New Probabilistic Models for Dependency Parsing: An Exploration

CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

Randomized Greedy Inference for Joint Segmentation, POS Tagging and Dependency Parsing

A Fast and Accurate Dependency Parser using Neural Networks

Very high accuracy and fast dependency parsing is not a contradiction

Dependency Parsing

MaltParser: A language-independent system for data-driven dependency parsing

An Efficient Algorithm for Projective Dependency Parsing

Field of Study

Venue Information

Name

Type

URL

Alternate Names