GenKIE: Robust Generative Multimodal Document Key Information Extraction

Panfeng Cao, Ye Wang, Qiang Zhang, Zaiqiao Meng


Abstract
Key information extraction (KIE) from scanned documents has gained increasing attention because of its applications in various domains. Although promising results have been achieved by some recent KIE approaches, they are usually built based on discriminative models, which lack the ability to handle optical character recognition (OCR) errors and require laborious token-level labeling. In this paper, we propose a novel generative end-to-end model, named GenKIE, to address the KIE task. GenKIE is a sequence-to-sequence multimodal generative model that utilizes multimodal encoders to embed visual, layout and textual features and a decoder to generate the desired output. Well-designed prompts are leveraged to incorporate the label semantics as the weakly supervised signals and entice the generation of the key information. One notable advantage of the generative model is that it enables automatic correction of OCR errors. Besides, token-level granular annotation is not required. Extensive experiments on multiple public real-world datasets show that GenKIE effectively generalizes over different types of documents and achieves state-of-the-art results. Our experiments also validate the model’s robustness against OCR errors, making GenKIE highly applicable in real-world scenarios.
Anthology ID:
2023.findings-emnlp.979
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14702–14713
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.979
DOI:
10.18653/v1/2023.findings-emnlp.979
Bibkey:
Cite (ACL):
Panfeng Cao, Ye Wang, Qiang Zhang, and Zaiqiao Meng. 2023. GenKIE: Robust Generative Multimodal Document Key Information Extraction. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 14702–14713, Singapore. Association for Computational Linguistics.
Cite (Informal):
GenKIE: Robust Generative Multimodal Document Key Information Extraction (Cao et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.979.pdf