arXiv cs.CL· Sujith Subramanian, P N Bhargav Teja, Susen Sarkar, Rajasekhara Reddy Duvvuru Muni·· 6 天前AI 评分20
专利权利要求无监督分类的嵌入几何与聚类算法基准测试
Benchmarking Embedding Geometries and Clustering Algorithms for Unsupervised Patent Claim Classification
AI 导读
研究在 45,000 项美国专利上训练双曲与欧氏 VAE（96 次运行、6 个种子），双曲模型在 3,000 次查询的 top-10 结果中检索到真正跨类别现有技术的比例为 18.76%，比欧氏模型的 12.34% 高 52%。
正文 · 原文
Abstract:Prior-art retrieval systems are structurally organized around classification codes, making cross-code discovery difficult. This paper asks if an unsupervised representation trained on patent text can recover relevant connections that code-restricted search cannot, and if hyperbolic space helps. We trained a hyperbolic and a matched Euclidean Variational Autoencoder (VAE) on 45,000 US patents (96 runs, 6 seeds). The hyperbolic model retrieves genuinely cross-category prior art 52% more often than the Euclidean model (18.76% vs. 12.34% of top-10 results, 3,000 queries). This represents a practical gain for the motivating search problem. The hyperbolic model agrees less with official classification (NMI 0.2392 vs. 0.3206), which we explain geometrically: the two measures capture different goals, and only one aligns with prior-art search needs. In a study of 10 technology domains (50,000 more patents), we find that a domain's classification breadth--the number of distinct CPC subgroups spanned--predicts approach performance (Pearson r=-0.642, p=0.045, N=10), and that patents per subgroup is an even stronger predictor (r=0.715, p=0.020). This provides a checkable signal for practitioners to determine where the method is most valuable. We report all findings with statistical transparency and release a complete, 91-test automated implementation.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.12997 [cs.AI] |
| (or arXiv:2610.12997v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12997 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Susen Sarkar [view email]
[v1]
Fri, 9 Oct 2026 05:02:37 UTC (2,168 KB)
来源：arXiv cs.CL · arxiv.org