arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.09487cs.DBcs.AIcs.LG

对应关系即决策:JevNexus 用于以决策为中心的模式匹配

Correspondences as Decisions: JevNexus for Decision-Centric Schema Matching

Runze Li, Hanchen Wang, Ying Zhang, Wenjie Zhang

首次发表
浏览论文内容

中文总结 AI 辅助

JevNexus 将模式匹配视为有界的对应关系决策,结合类型化成对决策与证据,仅在证据不一致时进行列表式细化,在保持匹配质量的同时大幅降低延迟。

中文摘要 AI 辅助

模式匹配越来越多地使用生成式语言模型对检索到的列候选进行重排序,尽管底层任务是一个有界的对应关系决策。我们提出了 JevNexus,它将类型化的成对决策与模式/实例证据相结合,并且仅在证据不一致且融合边际较小时才调用列表式细化。评估涵盖了来自六个基准家族的 561 个案例。JevNexus 获得了数据集宏平均 MRR 和 Hits@1 分别为 0.930 和 0.909,而 Magneto 为 0.926 和 0.903,同时将平均延迟从 123.452 秒降低到 15.929 秒(7.750 倍)。配对分析发现 MRR 或 Hits@1 均无统计学显著差异。该门控仅对 5.665% 的源列调用列表式细化,并避免了无条件细化导致的性能下降。代码和实验工件可在该 https URL 获取。

英文摘要

Schema matching increasingly uses generative language models to rerank retrieved column candidates, although the underlying task is a bounded correspondence decision. We present JevNexus, which combines typed pairwise decisions with schema/instance evidence and invokes listwise refinement only when the evidence disagrees and the fused margin is small. The evaluation covers 561 cases from six benchmark families. JevNexus obtains dataset-macro MRR and Hits@1 of 0.930 and 0.909, compared with 0.926 and 0.903 for Magneto, while reducing mean latency from 123.452 to 15.929 seconds (7.750). Paired analysis finds no statistically significant difference in either MRR or Hits@1. The gate invokes listwise refinement for only 5.665% of source columns and avoids the degradation caused by unconditional refinement. Code and experimental artifacts are available at https://github.com/RazeenLI/JevNexus.

发表机构

  • University of New South Wales(新南威尔士大学)
  • University of Technology Sydney(悉尼科技大学)

机构由 AI 辅助整理,请以论文原文为准。

补充信息

↑