Patent Representation Learning via Self-supervision
Zuo, You, Gerdes, Kim, de La Clergerie, Eric Villemonte, Sagot, Benoît
–arXiv.org Artificial Intelligence
This paper presents a simple yet effective contrastive learning framework for learning patent embeddings by leveraging multiple views from within the same document. We first identify a patent-specific failure mode of SimCSE style dropout augmentation: it produces overly uniform embeddings that lose semantic cohesion. To remedy this, we propose section-based augmentation, where different sections of a patent (e.g., abstract, claims, background) serve as complementary views. This design introduces natural semantic and structural diversity, mitigating over-dispersion and yielding embeddings that better preserve both global structure and local continuity. On large-scale benchmarks, our fully self-supervised method matches or surpasses citation-and IPC-supervised baselines in prior-art retrieval and classification, while avoiding reliance on brittle or incomplete annotations. Our analysis further shows that different sections specialize for different tasks-claims and summaries benefit retrieval, while background sections aid classification-highlighting the value of patents' inherent discourse structure for representation learning. These results highlight the value of exploiting intra-document views for scalable and generalizable patent understanding.
arXiv.org Artificial Intelligence
Nov-17-2025
- Country:
- Europe > France
- Île-de-France > Paris > Paris (0.04)
- North America > United States (0.46)
- Europe > France
- Genre:
- Research Report (1.00)
- Industry:
- Technology: