Deep Graph Convolutional Encoders for Structured Data to Text Generation

Published in

International Conference on Natural Language Ge...(2018)

External Links:

Generate Graph DownloadPDF

TL;DR

This paper proposes an alternative encoder based on graph convolutional networks that directly exploits the input structure and reports results on two graph-to-sequence datasets that empirically show the benefits of explicitly encoding the input graph structure.

Abstract

Most previous work on neural text generation from graph-structured data relies on standard sequence-to-sequence methods. These approaches linearise the input graph to be fed to a recurrent neural network. In this paper, we propose an alternative encoder based on graph convolutional networks that directly exploits the input structure. We report results on two graph-to-sequence datasets that empirically show the benefits of explicitly encoding the input graph structure.

Authors

Laura Perez-Beltrachini

4 papers

Diego Marcheggiani

1 papers

References54 items

Graph-to-Sequence Learning using Gated Graph Neural Networks

Relational inductive biases, deep learning, and graph networks

Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks

Bootstrapping Generators from Noisy Data

Evaluating Scoped Meaning Representations

Deep Graph Convolutional Encoders for Structured Data to Text Generation

Published in

International Conference on Natural Language Ge...(2018)

External Links:

Generate Graph DownloadPDF

TL;DR

Abstract

Authors

Laura Perez-Beltrachini

4 papers

Diego Marcheggiani

1 papers

References54 items

Graph-to-Sequence Learning using Gated Graph Neural Networks

Relational inductive biases, deep learning, and graph networks

Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks

Bootstrapping Generators from Noisy Data

Evaluating Scoped Meaning Representations

Shared Task Proposal: Multilingual Surface Realization Using Universal Dependency Trees

Linguistic realisation as machine translation: Comparing different MT models for AMR-to-text generation

The WebNLG Challenge: Generating Text from RDF Data

Creating Training Corpora for NLG Micro-Planners

Challenges in Data-to-Document Generation

Neural AMR: Sequence-to-Sequence Models for Parsing and Generation

Graph Convolutional Encoders for Syntax-aware Neural Machine Translation

Transition-Based Deep Input Linearization

Get To The Point: Summarization with Pointer-Generator Networks

Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling

OpenNMT: Open-Source Toolkit for Neural Machine Translation

Building RDF Content for Data-to-Text Generation

Semi-Supervised Classification with Graph Convolutional Networks

Densely Connected Convolutional Networks

Neural Text Generation from Structured Data with Application to the Biography Domain

Deep Residual Learning for Image Recognition

What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignment

Effective Approaches to Attention-based Neural Machine Translation

Adam: A Method for Stochastic Optimization

GloVe: Global Vectors for Word Representation

Sequence to Sequence Learning with Neural Networks

Neural Machine Translation by Jointly Learning to Align and Translate

Meteor Universal: Language Specific Translation Evaluation for Any Target Language

The Stanford CoreNLP Natural Language Processing Toolkit

Abstract Meaning Representation for Sembanking

The First Surface Realisation Shared Task: Overview and Evaluation Results

The Proposition Bank: An Annotated Corpus of Semantic Roles

Bleu: a Method for Automatic Evaluation of Machine Translation

Long Short-Term Memory

Dropout: a simple way to prevent neural networks from overfitting

Stumaba : From deep representation to surface

The Graph Neural Network Model

The Description Logic Handbook: Preface

A Study of Translation Edit Rate with Targeted Human Annotation

A STUDY OF TRANSLATION ERROR RATE WITH TARGETED HUMAN ANNOTATION

Annotating Noun Argument Structure for NomBank

The Description Logic Handbook: Theory, Implementation, and Applications

Gradient-based learning applied to document recognition

LSTM Adisham Hall was built in 1927 and completed in

LSTM William Anders was a crew member of the OPERATOR operated Apollo 8 and retired on September 1st 1969

LSTM The Archarya Institute of Technology are blue , white and was given the

WebNLG (William Anders dateOfRetirement 1969 - 09 - 01) (Apollo 8 commander Frank Borman) (William Anders was a crew member of Apollo 8) (Apollo 8 backup pilot

A.2 More example outputs Table 5 shows additional examples of generated texts for source WebNLG and SR11Deep graphs

WebNLG (Adisham Hall location Sri Lanka) (Adisham Hall architecturalStyle Tudor Revival architecture) (Adisham Hall completionDate 1931)

william anders , who retired on the 1st of september 1969 , was a crew member on apollo 8 along with commander frank borman and backup pilot buzz aldrin

a crew member of OPERATOR ’ s Apollo 8 alongside backup pilot Buzz Aldrin and backup pilot Buzz Aldrin

GCN Adirondack Regional Airport serves the city of Saranac Lake , which is part of Harrietstown , Essex County , New York , United States

institute of technology was given the ’ technical campus ’ status by the all india council for technical education which has blue , white and orange

the acharya institute of technology was established in 2000 and is governed by the international tennis federation

Field of Study

Computer Science

Journal Information

Name

ArXiv

Volume

abs/2005.00687

Venue Information

Name

International Conference on Natural Language Generation

Type

conference

URL

http://www.wikicfp.com/cfp/program?id=1613

Alternate Names

Int Conf Nat Lang Gener
INLG