Journal of Data and Information Science ›› 2022, Vol. 7 ›› Issue (3): 49-70.doi: 10.2478/jdis-2022-0015

• Research Paper • Previous Articles     Next Articles

A Use Case of Patent Classification Using Deep Learning with Transfer Learning

Roberto Henriques(), Adria Ferreira, Mauro Castelli   

  1. Campus de Campolide, Lisboa 1070-312, Portugal
  • Received:2022-03-12 Revised:2022-06-09 Accepted:2022-07-04 Online:2022-07-20 Published:2022-07-29
  • Contact: Roberto Henriques E-mail:roberto@novaims.unl.pt

Abstract:

Purpose: Patent classification is one of the areas in Intellectual Property Analytics (IPA), and a growing use case since the number of patent applications has been increasing worldwide. We propose using machine learning algorithms to classify Portuguese patents and evaluate the performance of transfer learning methodologies to solve this task.
Design/methodology/approach: We applied three different approaches in this paper. First, we used a dataset available by INPI to explore traditional machine learning algorithms and ensemble methods. After preprocessing data by applying TF-IDF, FastText and Doc2Vec, the models were evaluated by cross-validation in 5 folds. In a second approach, we used two different Neural Networks architectures, a Convolutional Neural Network (CNN) and a bi-directional Long Short-Term Memory (BiLSTM). Finally, we used pre-trained BERT, DistilBERT, and ULMFiT models in the third approach.
Findings: BERTTimbau, a BERT architecture model pre-trained on a large Portuguese corpus, presented the best results for the task, even though with a performance of only 4% superior to a LinearSVC model using TF-IDF feature engineering.
Research limitations: The dataset was highly imbalanced, as usual in patent applications, so the classes with the lowest samples were expected to present the worst performance. That result happened in some cases, especially in classes with less than 60 training samples.
Practical implications: Patent classification is challenging because of the hierarchical classification system, the context overlap, and the underrepresentation of the classes. However, the final model presented an acceptable performance given the size of the dataset and the task complexity. This model can support the decision and improve the time by proposing a category in the second level of ICP, which is one of the critical phases of the grant patent process.
Originality/value: To our knowledge, the proposed models were never implemented for Portuguese patent classification.

Key words: Natural Language Processing (NLP), Patent classification, Transfer Learning, Bi-directional Encoder Representations for Transformers (BERT)