GenVer：基于三元组到文本对齐的知识图谱验证方法
Bridging Structure and Semantics: Knowledge Graph Verification via Triple-to-Text Alignment
AI 导读
arXiv 论文提出生成式验证器 GenVer，利用三元组序列化形式与生成的自然语言表示（NLR）对知识图谱三元组进行评分。方法通过三元组-文本对齐选取训练对训练 seq2seq 生成器，再由 BERT 分类器融合特征。在基于 FB15k 构建的四个 FactFB 变体上，GenVer 取得 88.56% 至 91.52% 的最高分类准确率，但案例分析也暴露出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.AI · arxiv.org