Lightweight Spatial Modeling for Combinatorial Information Extraction From Documents

Yanfei Dong, Lambert Deng, Jiazheng Zhang, Xiaodong Yu, Ting Lin, Francesco Gelli, Soujanya Poria, Wee Sun Lee


Abstract
Documents that consist of diverse templates and exhibit complex spatial structures pose a challenge for document entity classification. We propose KNN-Former, which incorporates a new kind of spatial bias in attention calculation based on the K-nearest-neighbor (KNN) graph of document entities. We limit entities’ attention only to their local radius defined by the KNN graph. We also use combinatorial matching to address the one-to-one mapping property that exists in many documents, where one field has only one corresponding entity. Moreover, our method is highly parameter-efficient compared to existing approaches in terms of the number of trainable parameters. Despite this, experiments across various datasets show our method outperforms baselines in most entity types. Many real-world documents exhibit combinatorial properties which can be leveraged as inductive biases to improve extraction accuracy, but existing datasets do not cover these documents. To facilitate future research into these types of documents, we release a new ID document dataset that covers diverse templates and languages. We also release enhanced annotations for an existing dataset.
Anthology ID:
2023.findings-eacl.108
Volume:
Findings of the Association for Computational Linguistics: EACL 2023
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1471–1484
Language:
URL:
https://aclanthology.org/2023.findings-eacl.108
DOI:
10.18653/v1/2023.findings-eacl.108
Bibkey:
Cite (ACL):
Yanfei Dong, Lambert Deng, Jiazheng Zhang, Xiaodong Yu, Ting Lin, Francesco Gelli, Soujanya Poria, and Wee Sun Lee. 2023. Lightweight Spatial Modeling for Combinatorial Information Extraction From Documents. In Findings of the Association for Computational Linguistics: EACL 2023, pages 1471–1484, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Lightweight Spatial Modeling for Combinatorial Information Extraction From Documents (Dong et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2023.findings-eacl.108.pdf
Video:
 https://preview.aclanthology.org/dois-2013-emnlp/2023.findings-eacl.108.mp4