Work

Fact-Aware Generative Text Summarization with Dependency Graphs

Year: 2024

Type: article

Abstract: Generative text summaries often suffer from factual inconsistencies, where the summary deviates from the original text. This significantly reduces their usefulness. To address this issue, we propose a novel method for improving the factual accuracy of Chinese summaries by leveraging dependency graphs. Our approach involves analyzing the input text to build a dependency graph. This graph, along with the original text, is then processed by separate models: a Relational Graph Attention Neural Network for the dependency graph and a Transformer model for the text itself. Finally, a Transformer decoder generates the summary. We evaluate the factual consistency of the generated summaries using various methods. Experiments demonstrate that our approach improves about 7.79 points compared to the baseline Transformer model on the Chinese LCSTS dataset using ROUGE-1 metric, and 4.48 points in the factual consistency assessment model StructBERT.

Source: Electronics

DOI: 10.3390/electronics13163230

Authors: Ruoyu Chen, Yan Li, Yuru Jiang, Bochen Sun, Jingqi Wang, Zhen Li

Institutions: Beijing Information Science & Technology University, Beijing Institute of Technology

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,728

Funder: Natural Science Foundation of Beijing Municipality