Toward Subgraph-Guided Knowledge Graph Question Generation With Graph Neural Networks (2020-04-13T00:00:00.000000Z)

TL;DR

This work proposes to apply a bidirectional Graph2Seq model to encode the KG subgraph, and enhances the RNN decoder with a node-level copying mechanism to allow direct copying of node attributes from the KG subgraph to the output question.

Abstract

Knowledge graph (KG) question generation (QG) aims to generate natural language questions from KGs and target answers. Previous works mostly focus on a simple setting that is to generate questions from a single KG triple. In this work, we focus on a more realistic setting where we aim to generate questions from a KG subgraph and target answers. In addition, most previous works built on either RNN- or Transformer-based models to encode a linearized KG subgraph, which totally discards the explicit structure information of a KG subgraph. To address this issue, we propose to apply a bidirectional Graph2Seq model to encode the KG subgraph. Furthermore, we enhance our RNN decoder with a node-level copying mechanism to allow direct copying of node attributes from the KG subgraph to the output question. Both automatic and human evaluation results demonstrate that our model achieves new state-of-the-art scores, outperforming existing methods by a significant margin on two QG benchmarks. Experimental results also show that our QG model can consistently benefit the question-answering (QA) task as a means of data augmentation.

Authors

Lingfei Wu

11 papers

Yu Chen

2 papers

Mohammed J. Zaki

2 papers

TL;DR

Abstract

Authors

References126 items

Diversified Query Generation Guided by Knowledge Graph

Generating Factoid Questions with Question Type Enhanced Representation and Attention-based Copy Mechanism

Compact Graph Structure Learning via Mutual Information Compression

JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs

Deep Learning on Graphs for Natural Language Processing

Personalized Food Recommendation as Constrained Question Answering over a Large-scale Food Knowledge Graph

Knowledge-enriched, Type-constrained and Grammar-guided Question Generation over Knowledge Bases

Retrieval-Augmented Generation for Code Summarization via Hybrid GNN

Automatic Code Summarization via Multi-dimensional Semantic Fusing in GNN

Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings

Semantic Graphs for Generating Deep Questions

A self-attention based message passing neural network for predicting molecular lipophilicity and aqueous solubility

GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation

Deep Iterative and Adaptive Learning for Graph Neural Networks

A deeper graph neural network for recommender systems

Generating Questions for Knowledge Bases via Incorporating Diversified Contexts and Answer-Aware Loss

Difficulty-Controllable Multi-hop Question Generation from Knowledge Graphs

FoodKG: A Semantics-Driven Knowledge Graph for Food Recommendation

Two Birds, One Stone: A Simple, Unified Model for Text Generation from Structured and Unstructured Data

Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation

Enhancing AMR-to-Text Generation with Dual Graph Representations

DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversation

Graph Contextualized Self-Attention Network for Session-based Recommendation

GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension

Graph convolutional networks for computational drug development and discovery

GSN: A Graph-Structured Network for Multi-Party Dialogues

Graph U-Nets

Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systems

Drug-Drug Adverse Effect Prediction with Graph Co-Attention

Text Generation from Knowledge Graphs with Graph Transformers

Learning Discrete Structures for Graph Neural Networks

Bidirectional Attentive Memory Networks for Question Answering over Knowledge Bases

Graph Neural Networks for Social Recommendation

Graph Convolutional Neural Networks for Predicting Drug-Target Interactions

Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering

Deep Graph Convolutional Encoders for Structured Data to Text Generation

Graph Convolutional Networks for Text Classification

SQL-to-Text Generation with Graph-to-Sequence Model

Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text

Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model

Deep Reasoning with Knowledge Graph for Social Relationship Understanding

Graph-to-Sequence Learning using Gated Graph Neural Networks

Hierarchical Graph Representation Learning with Differentiable Pooling

Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation

Graph Convolutional Neural Networks for Web-Scale Recommender Systems

Relational inductive biases, deep learning, and graph networks

Learning Conditioned Graph Structures for Interpretable Visual Question Answering

Leveraging Context Information for Natural Question Generation

A Graph-to-Sequence Model for AMR-to-Text Generation

Table-to-Text: Describing Table Region With Natural Language

Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks

The Web as a Knowledge-Base for Answering Complex Questions

Zero-Shot Question Generation from Knowledge Graphs for Unseen Predicates and Entity Types

An Interpretable Reasoning Network for Multi-Relation Question Answering

Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples

Graph Attention Networks

Visual Question Generation as Dual Task of Visual Question Answering

Attention is All you Need

Inductive Representation Learning on Large Graphs

Question Answering and Question Generation as Dual Tasks

A Deep Reinforced Model for Abstractive Summarization

Learning to Ask: Neural Question Generation for Reading Comprehension

Graph Convolutional Encoders for Syntax-aware Neural Machine Translation

Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs

Neural Message Passing for Quantum Chemistry

Get To The Point: Summarization with Pointer-Generator Networks

Generating Natural Language Question-Answer Pairs from a Knowledge Graph Using a RNN Based Question Generation Model

OpenNMT: Open-Source Toolkit for Neural Machine Translation

Self-Critical Sequence Training for Image Captioning

Geometric Deep Learning: Going beyond Euclidean data

Knowledge Questions from Knowledge Graphs

Question Generation from a Knowledge Base with Web Exploration

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation

Graph-Structured Representations for Visual Question Answering

Semi-Supervised Classification with Graph Convolutional Networks

The Value of Semantic Parse Labeling for Knowledge Base Question Answering