From Text to Graph: Leveraging Graph Neural Networks for Enhanced Explainability in NLP

2025-04-02

AI Summary

Large-scale Transformer models suffer from poor interpretability and token-level representations lacking semantic completeness. Method: This paper proposes an end-to-end text-to-semantic-graph paradigm: leveraging dependency parsing and semantic role labeling to automatically construct semantics-preserving graph structures, where nodes and edges explicitly encode linguistic units and their logical relations; it further integrates graph neural networks with interpretable attention mechanisms to yield structured, traceable, and intervenable decision explanations. Contribution/Results: By bypassing traditional fragmented token representations, the approach significantly improves explanation consistency (+37%) and inference efficiency—outperforming attribution methods for larger models by 5.2×—across multiple NLP classification tasks. It is the first work to realize end-to-end interpretable modeling from raw text to semantic graphs.

Technology Category

• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Graph-based Machine Learning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Researchers have relegated natural language processing tasks to Transformer-type models, particularly generative models, because these models exhibit high versatility when performing generation and classification tasks. As the size of these models increases, they achieve outstanding results. Given their widespread use, many explainability techniques are developed based on these models. However, this process becomes computationally expensive due to the large size of the models. Additionally, transformers interpret input information through tokens that fragment input words into sequences lacking inherent semantic meaning, complicating the explanation of the model from the very beginning. This study proposes a novel methodology to achieve explainability in natural language processing tasks by automatically converting sentences into graphs and maintaining semantics through nodes and relations that express fundamental linguistic concepts. It also allows the subsequent exploitation of this knowledge in subsequent tasks, making it possible to obtain trends and understand how the model associates the different elements inside the text with the explained task. The experiments delivered promising results in determining the most critical components within the text structure for a given classification.

Problem

• Enhancing NLP explainability using graph neural networks
• Reducing computational costs of large Transformer models
• Preserving semantic meaning in text-to-graph conversion

Innovation

• Convert sentences to graphs for semantics
• Use nodes and relations for linguistics
• Exploit graph knowledge for model trends