PLoS ONE· 2026Q1
PaECTER: Patent-level representation learning using citation-informed transformers
- 30citations
- Q1SCImago
- 2026year
Short summary
PaECTER, a new transformer model fine-tuned with examiner-added citation data, generates numerical patent representations that outperform current state-of-the-art models in similarity tasks.
AI-generated from the title and abstract; the full text is not read.
Key points
- PaECTER is a novel transformer model fine-tuned with examiner-added citation data for patent representation.
- It outperforms BERT for Patents and general text embedding models (E5, GTE, BGE) on patent citation prediction.
- PaECTER achieves an average rank of 1.32 for identifying the most similar patent among 25 irrelevant ones.
- The generated numerical representations are suitable for downstream tasks like classification, knowledge flow tracing, and semantic similarity search.
AI-generated from the title and abstract; the full text is not read.
Abstract
PaECTER is an open-source document-level encoder specific to patents. We fine-tune BERT for Patents with examiner-added citation information to generate numerical representations for patent documents. PaECTER performs better in similarity tasks than current state-of-the-art models used in the patent domain. More specifically, our model outperforms the patent specific pre-trained language model (BERT for Patents) and general-purpose text embedding models (e.g., E5, GTE, and BGE) on our patent citation prediction test dataset on different rank evaluation metrics. PaECTER predicts at least one most similar patent at a rank of 1.32 on average when compared against 25 irrelevant patents. Numerical representations generated by PaECTER from patent text can be used for downstream tasks such as classification, tracing knowledge flows, or semantic similarity search. Semantic similarity search is especially relevant in the context of prior art search for both inventors and patent examiners.
The authors' abstract, as published at the source. PLoS ONE, 2026 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Artificial Intelligence
Artificial IntelligenceComputer Science