Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

natural-language-processing-2

KG-to-Text Generation

3260 papers • 126 benchmarks • 313 datasets

Knowledge-graph-to-text (KG-to-text) generation aims to generate high-quality texts which are consistent with input graphs. Description from: JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in kg-to-text-generation-4

Trend

Dataset

Best Model

Actions

WebNLG 2.0 (Unconstrained)

WebNLG 2.0 (Unconstrained)

AGENDA

AGENDA

EventNarrative

Libraries

i

Use these libraries to find kg-to-text-generation-4 models and implementations

Datasets

WebQuestions

WebNLG

AGENDA

PathQuestion

GenWiki

WikiGraphs

Subtasks

No subtasks available.

Most implemented papers

Investigating Pretrained Language Models for Graph-to-Text Generation

Leonardo F. R. Ribeiro, Martin Schmitt, Hinrich Schütze, Iryna Gurevych•Wed Jul 15 2020

It is suggested that the PLMs benefit from similar facts seen during pretraining or fine-tuning, such that they perform well even when the input graph is reduced to a simple bag of node and edge labels.

226

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

EventNarrative

WebQuestions

WebQuestions

PathQuestion

PathQuestion

WebNLG 2.0 (Constrained)

WebNLG 2.0 (Constrained)

WikiGraphs

WikiGraphs

WebNLG (All)

WebNLG (All)

WebNLG (Seen)

WebNLG (Seen)

WebNLG (Unseen)

WebNLG (Unseen)

ENT-DESC

ENT-DESC

XAlign

XAlign

EventNarrative

ENT-DESC

0

Text Generation from Knowledge Graphs with Graph Transformers

Mirella Lapata, Hannaneh Hajishirzi, Yi Luan, Rik Koncel-Kedziorski, Dhanush Bekal•Sun Mar 31 2019

This work addresses the problem of generating coherent multi-sentence texts from the output of an information extraction system, and in particular a knowledge graph by introducing a novel graph transforming encoder which can leverage the relational structure of such knowledge graphs without imposing linearization or hierarchical constraints.

347 0

Deep Graph Convolutional Encoders for Structured Data to Text Generation

Laura Perez-Beltrachini, Diego Marcheggiani•Mon Oct 22 2018

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.

126 0

Handling Rare Items in Data-to-Text Generation

Claire Gardent, Anastasia Shimorina•Wed Oct 31 2018

It is shown that rare items strongly impact performance and that combining delexicalisation and copying yields the strongest improvement; that copying underperforms for rare and unseen items and that the impact of these two mechanisms greatly varies depending on how the dataset is constructed and on how it is split into train, dev and test.

43 0

Toward Subgraph-Guided Knowledge Graph Question Generation With Graph Neural Networks

Lingfei Wu, Yu Chen, Mohammed J. Zaki•Sun Apr 12 2020

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.

62 0

Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs

Leonardo F. R. Ribeiro, Claire Gardent, Iryna Gurevych, Yue Zhang•Tue Jan 28 2020

This work gathers both encoding strategies, proposing novel neural models that encode an input graph combining both global and local node contexts, in order to learn better contextualized node embeddings.

78 0

ENT-DESC: Entity Description Generation by Exploring Knowledge Graph

Liying Cheng, Dekun Wu, Lidong Bing, Yan Zhang, Zhanming Jie, Wei Lu, Luo Si•Wed Apr 29 2020

A large-scale and challenging dataset that involves retrieving abundant knowledge of various types of main entities from a large knowledge graph (KG), which makes the current graph-to-sequence models severely suffer from the problems of information loss and parameter explosion while generating the descriptions.

22 0

Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models

Wayne Xin Zhao, Ji-rong Wen, Tianyi Tang, N. Yuan, Junyi Li, Zhicheng Wei•Wed Jun 02 2021

This paper studies how to automatically generate a natural language text that describes the facts in knowledge graph (KG) and makes three major technical contributions, namely representation alignment for bridging the semantic gap between KG encodings and PLMs, relation-biased KG linearization for deriving better input representations, and multi-task learning for learning the correspondence betweenKG and text.

58 0

How to Train Your Agent to Read and Write

Mingkui Tan, Qi Wu, Guanghui Xu, Li Liu, Mengge He•Sun Jan 03 2021

A Deep ReAder-Writer (DRAW) network, which consists of a Reader that can extract knowledge graphs from input paragraphs and discover potential knowledge, a graph-to-text Writer that generates a novel paragraph, and a Reviewer that reviews the generated paragraph from three different aspects.

3 0

KGLM: Pretrained Knowledge-Grounded Language Model for Data-to-Text Generation

Yu Su, Wenhu Chen, Xifeng Yan, W. Wang•Sun Oct 04 2020

A knowledge-grounded pre-training (KGPT), which consists of two parts, 1) a general knowledge-grounded generation model to generate knowledge-enriched text and 2) a pre-training paradigm on a massive knowledge-grounded text corpus crawled from the web.

26 0

Adding a benchmark result helps the community track progress.

KG-to-Text Generation | State-of-the-Art