Document Type

Conference Paper

Publication Date




Publication Title

JCDL '22: Proceedings of the 22nd ACM/IEEE Joint Conference on Digital Libraries


20 (1-5)

Conference Name

JCDL '22: The ACM/IEEE Joint Conference on Digital Libraries in 2022, June 20-24, 2022, Cologne, Germany


Technical drawings used for illustrating designs are ubiquitous in patent documents, especially design patents. Different from natural images, these drawings are usually made using black strokes with little color information, making it challenging for models trained on natural images to recognize objects. To facilitate indexing and searching, we propose an effective and efficient visual descriptor model that extracts object names and aspects from patent captions to annotate benchmark patent figure datasets. We compared two state-of-the-art named entity recognition (NER) models and found that with a limited number of annotated samples, the BiLSTM-CRF model outperforms the Transformer model by a significant margin, achieving an overall F1=96.60%. We further conducted a data efficiency study by varying the number of training samples and found that BiLSTM consistently beats the transformer model on our task. The proposed model is used to annotate a benchmark patent figure dataset.


© 2022 Copyright held by the owner/authors

This work is licensed under a Creative Commons Attribution International 4.0 License (CC BY 4.0).

Original Publication Citation

Wei, X., Wu, J., Ajayi, K., & Oyen, D. (2022). Visual descriptor extraction from patent figure captions: A case study of data efficiency between BiLSTM and transformer. JCDL '22: Proceedings of the 22nd ACM/IEEE Joint Conference on Digital Libraries (20, pp. 1-5). Association for Computing Machinery.


0000-0003-0173-4463 (Wu), 0000-0002-5124-0739 (Ajayi)