loading page

Automated patent classification for crop protection via domain adaptation
  • +2
  • Dimitrios Christofidellis,
  • Marzena Maria Lehmann,
  • Torsten Luksch,
  • Marco Stenta,
  • Matteo Manica
Dimitrios Christofidellis
Queen's University Belfast

Corresponding Author:dchristofidellis01@qub.ac.uk

Author Profile
Marzena Maria Lehmann
Syngenta Crop Protection AG
Author Profile
Torsten Luksch
Syngenta Crop Protection AG
Author Profile
Marco Stenta
Syngenta Crop Protection AG
Author Profile
Matteo Manica
IBM Research
Author Profile

Abstract

Patents show how technology evolves in most scientific fields over time. The best way to use this valuable knowledge base is to use efficient and effective information retrieval and searches for related prior art. Patent classification, i.e., assigning a patent to one or more predefined categories, is a fundamental step towards synthesizing the information content of an invention. To this end, architectures based on Transformers, especially those derived from the BERT family have already been proposed in the literature and they have shown remarkable results by setting a new state-of-the-art performance for the classification task. Here, we study how domain adaptation can push the performance boundaries in patent classification by rigorously evaluating and implementing a collection of recent transfer learning techniques, e.g., domain-adaptive pretraining and adapters. Our analysis shows how leveraging these advancements enables the development of state-of-the-art models with increased precision, recall, and F1-score. We base our evaluation on both standard patent classification datasets derived from patent offices-defined code hierarchies and more practical real-world use-case scenarios containing labels from the agrochemical industrial domain. The application of these domain adapted techniques to patent classification in a multilingual setting is also examined and evaluated.
23 Nov 2022Submitted to Applied AI Letters
24 Nov 2022Submission Checks Completed
24 Nov 2022Assigned to Editor
29 Nov 2022Reviewer(s) Assigned
20 Dec 2022Review(s) Completed, Editorial Evaluation Pending
21 Dec 2022Editorial Decision: Revise Minor
25 Jan 20231st Revision Received
29 Jan 2023Submission Checks Completed
29 Jan 2023Assigned to Editor
31 Jan 2023Reviewer(s) Assigned
06 Feb 2023Review(s) Completed, Editorial Evaluation Pending
06 Feb 2023Editorial Decision: Accept