arXiv cs.CL· Ziang Cui·· 11 小时前AI 评分24
GenVer：用三元组到文本对齐做知识图谱验证
Bridging Structure and Semantics: Knowledge Graph Verification via Triple-to-Text Alignment
AI 导读
GenVer 是一个生成式验证器，通过三元组的序列化形式与生成的自然语言表示（NLR）联合打分，并用三元组-文本对齐流程筛选训练对，再由 BERT 分类器融合两类特征。在基于 FB15k 构建的四个 FactFB 变体上，其分类准确率达 88.56% 至 91.52%，为所评估基线中最高。案例分析同时暴露了语义漂移与高置信度错误。
正文 · 原文
Abstract:Semantic accuracy is an important dimension of knowledge graph quality. Graph-based scoring methods exploit relational structure, while textual representations allow classifiers to draw on knowledge encoded by pre-trained language models (PLMs). We present GenVer, a generative verifier that scores triples using both their serialized form and generated natural language representations (NLRs). A triple-text alignment procedure selects training pairs for a sequence-to-sequence generator; a BERT-based classifier then combines features from each triple and its generated NLR. On four FactFB variants, constructed from FB15k using perturbed negative triples, GenVer obtains the highest classification accuracy among the evaluated baselines, ranging from 88.56% to 91.52%. The experiments suggest that generated representations can help triple classification, while the case analysis also exposes semantic drift and high-confidence errors.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.07780 [cs.CL] |
| (or arXiv:2611.07780v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.07780 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ziang Cui [view email]
[v1]
Thu, 5 Nov 2026 10:19:27 UTC (513 KB)
来源：arXiv cs.CL · arxiv.org