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

TL;DR

The Multi-Granularity Graph Structure Attention (MGSA) model is proposed, which integrates both granularities of information and allows the model to more comprehensively understand the information contained in the original knowledge graph, thereby improving the quality of the generated text.

Abstract

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.

Figures (4)

• Figure 1: The knowledge graph and its corresponding description text, with italic bold indicating relationship labels and colored highlights marking entities.
• Figure 2: Overall model architecture. The input consists of two levels of granularity in the linearization process. The encoder module incorporates structure attention at both granularities, while the decoder module follows the standard Transformer decoder structure.
• Figure 3: Entity-level linearization and word-level linearization.
• Figure 4: Impact of $\lambda$ values.