Graph Neural Networks for Natural Language Processing: A Survey

06/10/2021
by   Lingfei Wu, et al.
176

Deep learning has become the dominant approach in coping with various tasks in Natural LanguageProcessing (NLP). Although text inputs are typically represented as a sequence of tokens, there isa rich variety of NLP problems that can be best expressed with a graph structure. As a result, thereis a surge of interests in developing new deep learning techniques on graphs for a large numberof NLP tasks. In this survey, we present a comprehensive overview onGraph Neural Networks(GNNs) for Natural Language Processing. We propose a new taxonomy of GNNs for NLP, whichsystematically organizes existing research of GNNs for NLP along three axes: graph construction,graph representation learning, and graph based encoder-decoder models. We further introducea large number of NLP applications that are exploiting the power of GNNs and summarize thecorresponding benchmark datasets, evaluation metrics, and open-source codes. Finally, we discussvarious outstanding challenges for making the full use of GNNs for NLP as well as future researchdirections. To the best of our knowledge, this is the first comprehensive overview of Graph NeuralNetworks for Natural Language Processing.

READ FULL TEXT

page 3

page 18

page 20

page 22

research
03/18/2020

Pre-trained Models for Natural Language Processing: A Survey

Recently, the emergence of pre-trained models (PTMs) has brought natural...
research
11/05/2020

Semantic and Relational Spaces in Science of Science: Deep Learning Models for Article Vectorisation

Over the last century, we observe a steady and exponentially growth of s...
research
08/24/2021

Graph Neural Networks: Methods, Applications, and Opportunities

In the last decade or so, we have witnessed deep learning reinvigorating...
research
03/24/2021

Representing Numbers in NLP: a Survey and a Vision

NLP systems rarely give special consideration to numbers found in text. ...
research
04/30/2021

Summarization, Simplification, and Generation: The Case of Patents

We survey Natural Language Processing (NLP) approaches to summarizing, s...
research
07/25/2020

Constructing a Testbed for Psychometric Natural Language Processing

Psychometric measures of ability, attitudes, perceptions, and beliefs ar...
research
08/19/2020

A Survey on Text Simplification

Text Simplification (TS) aims to reduce the linguistic complexity of con...

Please sign up or login with your details

Forgot password? Click here to reset