{"title":"Edge-centric optimization: a novel strategy for minimizing information loss in graph-to-text generation","authors":"Zheng Yao, Jingyuan Li, Jianhe Cen, Shiqi Sun, Dahu Yin, Yuanzhuo Wang","doi":"10.1007/s40747-024-01690-y","DOIUrl":null,"url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>Given the remarkable text generation capabilities of pre-trained language models, impressive results have been realized in graph-to-text generation. However, while learning from knowledge graphs, these language models are unable to fully grasp the structural information of the graph, leading to logical errors and missing key information. Therefore, an important research direction is to minimize the loss of graph structural information during the model training process. We propose a framework named Edge-Optimized Multi-Level Information refinement (EMLR), which aims to maximize the retention of the graph’s structural information from an edge perspective. Based on this framework, we further propose a new graph generation model, named TriELMR, highlighting the comprehensive interactive learning relationship between the model and the graph structure, as well as the importance of edges in the graph structure. TriELMR adopts three main strategies to reduce information loss during learning: (1) Knowledge Sequence Optimization; (2) EMLR Framework; and (3) Graph Activation Function. Experimental results reveal that TriELMR exhibits exceptional performance across various benchmark tests, especially on the webnlgv2.0 and Event Narrative datasets, achieving BLEU-4 scores of <span>\\(66.5\\%\\)</span> and <span>\\(37.27\\%\\)</span>, respectively, surpassing the state-of-the-art models. These demonstrate the advantages of TriELMR in maintaining the accuracy of graph structural information.</p><h3 data-test=\"abstract-sub-heading\">Graphical abstract</h3>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"114 1","pages":""},"PeriodicalIF":5.0000,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Complex & Intelligent Systems","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s40747-024-01690-y","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
Abstract
Given the remarkable text generation capabilities of pre-trained language models, impressive results have been realized in graph-to-text generation. However, while learning from knowledge graphs, these language models are unable to fully grasp the structural information of the graph, leading to logical errors and missing key information. Therefore, an important research direction is to minimize the loss of graph structural information during the model training process. We propose a framework named Edge-Optimized Multi-Level Information refinement (EMLR), which aims to maximize the retention of the graph’s structural information from an edge perspective. Based on this framework, we further propose a new graph generation model, named TriELMR, highlighting the comprehensive interactive learning relationship between the model and the graph structure, as well as the importance of edges in the graph structure. TriELMR adopts three main strategies to reduce information loss during learning: (1) Knowledge Sequence Optimization; (2) EMLR Framework; and (3) Graph Activation Function. Experimental results reveal that TriELMR exhibits exceptional performance across various benchmark tests, especially on the webnlgv2.0 and Event Narrative datasets, achieving BLEU-4 scores of \(66.5\%\) and \(37.27\%\), respectively, surpassing the state-of-the-art models. These demonstrate the advantages of TriELMR in maintaining the accuracy of graph structural information.
期刊介绍：
Complex & Intelligent Systems aims to provide a forum for presenting and discussing novel approaches, tools and techniques meant for attaining a cross-fertilization between the broad fields of complex systems, computational simulation, and intelligent analytics and visualization. The transdisciplinary research that the journal focuses on will expand the boundaries of our understanding by investigating the principles and processes that underlie many of the most profound problems facing society today.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
