# MGSA: Multi-Granularity Graph Structure Attention for Knowledge Graph-to-Text Generation

arXiv: https://arxiv.org/abs/2409.10294 · HTML: https://mlsanity.com/paper/2409.10294/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 39 references that are in the map.
- First posted on arXiv 16 Sep 2024.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Text Generation from Knowledge Graphs with Graph Transformers](https://mlsanity.com/paper/1904.02342/) (2019)
- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2201.05273/) (2022)
- [Investigating Pretrained Language Models for Graph-to-Text Generation](https://mlsanity.com/paper/2007.08426/) (2020)
- [Retrieve-Rewrite-Answer: A KG-to-Text Enhanced LLMs Framework for Knowledge Graph Question Answering](https://mlsanity.com/paper/2309.11206/) (2023)
- [JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs](https://mlsanity.com/paper/2106.10502/) (2021)
- [ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models](https://mlsanity.com/paper/2310.08975/) (2023)
- [EventKG: A Multilingual Event-Centric Temporal Knowledge Graph](https://mlsanity.com/paper/1804.04526/) (2018)
- [Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs](https://mlsanity.com/paper/2001.11003/) (2020)
- [Densely Connected Graph Convolutional Networks for Graph-to-Sequence Learning](https://mlsanity.com/paper/1908.05957/) (2019)
- [GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text Generation](https://mlsanity.com/paper/2204.06674/) (2022)
- [EventNarrative: A large-scale Event-centric Dataset for Knowledge Graph-to-Text Generation](https://mlsanity.com/paper/2111.00276/) (2021)
- [Unifying Structured Data as Graph for Data-to-Text Pre-Training](https://mlsanity.com/paper/2401.01183/) (2024)
- [KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation](https://mlsanity.com/paper/2010.02307/) (2020)
- [A Systematic Review of Data-to-Text NLG](https://mlsanity.com/paper/2402.08496/) (2024)
- [AMR-to-Text Generation with Cache Transition Systems](https://mlsanity.com/paper/1912.01682/) (2019)
- [GraSAME: Injecting Token-Level Structural Information to Pretrained Language Models via Graph-guided Self-Attention Mechanism](https://mlsanity.com/paper/2404.06911/) (2024)
- [Knowledge Graph for NLG in the context of conversational agents](https://mlsanity.com/paper/2307.01548/) (2023)

## Built on by (most cited first, 2 of 2)

- [Factual and Edit-Sensitive Graph-to-Sequence Generation via Graph-Aware Adaptive Noising](https://mlsanity.com/paper/2604.24104/) (2026)
- [What Gets Unmasked First? Trajectory Analysis of Diffusion Models for Graph-to-Text Generation](https://mlsanity.com/paper/2605.31564/) (2026)

## Abstract (arXiv)

The Knowledge Graph-to-Text Generation task aims to convert structured knowledge graphs into coherent and human-readable natural language text. Recent efforts in this field have focused on enhancing pre-trained language models (PLMs) by incorporating graph structure information to capture the intricate structure details of knowledge graphs. However, most of these approaches tend to capture only single-granularity structure information, concentrating either on the relationships between entities within the original graph or on the relationships between words within the same entity or across different entities. This narrow focus results in a significant limitation: models that concentrate solely on entity-level structure fail to capture the nuanced semantic relationships between words, while those that focus only on word-level structure overlook the broader relationships between original entire entities. To overcome these limitations, this paper introduces the Multi-granularity Graph Structure Attention (MGSA), which is based on PLMs. The encoder of the model architecture features an entity-level structure encoding module, a word-level structure encoding module, and an aggregation module that synthesizes information from both structure. This multi-granularity structure encoding approach allows the model to simultaneously capture both entity-level and word-level structure information, providing a more comprehensive understanding of the knowledge graph's structure information, thereby significantly improving the quality of the generated text. We conducted extensive evaluations of the MGSA model using two widely recognized KG-to-Text Generation benchmark datasets, WebNLG and EventNarrative, where it consistently outperformed models that rely solely on single-granularity structure information, demonstrating the effectiveness of our approach.