paper-with-me

Papers

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

2025-04-02 · Fabio Yáñez-Romero, Andrés Montoyo, Armando Suárez, Yoan Gutiérrez, Ruslan Mitkov

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.

📄 PDF Abstract BibTeX arXiv:2504.02064

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Semantic Interpretation and Validation of Graph Attention-based Explanations for GNN Models

2023-08-08 · Efimia Panagiotaki, Daniele De Martini, Lars Kunze

In this work, we propose a methodology for investigating the use of semantic attention to enhance the explainability of Graph Neural Network (GNN)-based models. Graph Deep Learning (GDL) has emerged as a promising field …

Feature ImportanceGraph AttentionGraph Neural Network

SEEN: Sharpening Explanations for Graph Neural Networks using Explanations from Neighborhoods

2021-06-16 · Hyeoncheol Cho, Youngrock Oh, Eunjoo Jeon

Explaining the foundations for predictions obtained from graph neural networks (GNNs) is critical for credible use of GNN models for real-world problems. Owing to the rapid growth of GNN applications, recent progress in …

Node Classification

Empowering Domain-Specific Language Models with Graph-Oriented Databases: A Paradigm Shift in Performance and Model Maintenance

2024-10-04 · Ricardo Di Pasquale, Soledad Represa

In an era dominated by data, the management and utilization of domain-specific language have emerged as critical challenges in various application domains, particularly those with industry-specific requirements. Our work…

SES: Bridging the Gap Between Explainability and Prediction of Graph Neural Networks

2024-07-16 · Zhenhua Huang, Kunhao Li, Shaojie Wang, Zhaohong Jia 외

Despite the Graph Neural Networks' (GNNs) proficiency in analyzing graph data, achieving high-accuracy and interpretable predictions remains challenging. Existing GNN interpreters typically provide post-hoc explanations …

Contrastive LearningGraph Neural NetworkTriplet

Explainability in subgraphs-enhanced Graph Neural Networks

2022-09-16 · Michele Guerra, Indro Spinelli, Simone Scardapane, Filippo Maria Bianchi

Recently, subgraphs-enhanced Graph Neural Networks (SGNNs) have been introduced to enhance the expressive power of Graph Neural Networks (GNNs), which was proved to be not higher than the 1-dimensional Weisfeiler-Leman i…

Graph Classification