DocQueryNet: Value Retrieval with Arbitrary Queries for Form-like Documents

Mingfei Gao, Le Xue, Chetan Ramaiah, Chen Xing, Ran Xu, Caiming Xiong


Abstract
We propose, DocQueryNet, a value retrieval method with arbitrary queries for form-like documents to reduce human effort of processing forms. Unlike previous methods that only address a fixed set of field items, our method predicts target value for an arbitrary query based on the understanding of the layout and semantics of a form. To further boost model performance, we propose a simple document language modeling (SimpleDLM) strategy to improve document understanding on large-scale model pre-training. Experimental results show that DocQueryNet outperforms previous designs significantly and the SimpleDLM further improves our performance on value retrieval by around 17% F1 score compared with the state-of-the-art pre-training method. Code is available here, https://github.com/salesforce/QVR-SimpleDLM.
Anthology ID:
2022.coling-1.187
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
2141–2146
Language:
URL:
https://aclanthology.org/2022.coling-1.187
DOI:
Bibkey:
Cite (ACL):
Mingfei Gao, Le Xue, Chetan Ramaiah, Chen Xing, Ran Xu, and Caiming Xiong. 2022. DocQueryNet: Value Retrieval with Arbitrary Queries for Form-like Documents. In Proceedings of the 29th International Conference on Computational Linguistics, pages 2141–2146, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
DocQueryNet: Value Retrieval with Arbitrary Queries for Form-like Documents (Gao et al., COLING 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.coling-1.187.pdf
Code
 salesforce/qvr-simpledlm