Papers › Field Extraction from Forms with Unlabeled Data

Field Extraction from Forms with Unlabeled Data

8 Oct 2021SpaNLP (ACL) 2022 5arXiv:2110.04282archive 2025-07-28

Mingfei Gao, Zeyuan Chen, Nikhil Naik, Kazuma Hashimoto, Caiming Xiong, ran Xu

We propose a novel framework to conduct field extraction from forms with unlabeled data. To bootstrap the training process, we develop a rule-based method for mining noisy pseudo-labels from unlabeled forms. Using the supervisory signal from the pseudo-labels, we extract a discriminative token representation from a transformer-based model by modeling the interaction between text in the form. To prevent the model from overfitting to label noise, we introduce a refinement module based on a progressive pseudo-label ensemble. Experimental results demonstrate the effectiveness of our framework.

PaperPDFConference PDFCode

Code

salesforce/inv-cdip officialmentioned in paper report
salesforce/qvr-simpledlm mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Pseudo Label

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections