English

Patent Representation Learning via Self-supervision

Computation and Language 2025-11-17 v1 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2511.10657,
  title  = {Patent Representation Learning via Self-supervision},
  author = {You Zuo and Kim Gerdes and Eric Villemonte de La Clergerie and Benoît Sagot},
  journal= {arXiv preprint arXiv:2511.10657},
  year   = {2025}
}
R2 v1 2026-07-01T07:36:25.898Z