Form2Seq : A Framework for Higher-Order Form Structure Extraction

Milan Aggarwal, Hiresh Gupta, Mausoom Sarkar, Balaji Krishnamurthy


Abstract
Document structure extraction has been a widely researched area for decades with recent works performing it as a semantic segmentation task over document images using fully-convolution networks. Such methods are limited by image resolution due to which they fail to disambiguate structures in dense regions which appear commonly in forms. To mitigate this, we propose Form2Seq, a novel sequence-to-sequence (Seq2Seq) inspired framework for structure extraction using text, with a specific focus on forms, which leverages relative spatial arrangement of structures. We discuss two tasks; 1) Classification of low-level constituent elements (TextBlock and empty fillable Widget) into ten types such as field captions, list items, and others; 2) Grouping lower-level elements into higher-order constructs, such as Text Fields, ChoiceFields and ChoiceGroups, used as information collection mechanism in forms. To achieve this, we arrange the constituent elements linearly in natural reading order, feed their spatial and textual representations to Seq2Seq framework, which sequentially outputs prediction of each element depending on the final task. We modify Seq2Seq for grouping task and discuss improvements obtained through cascaded end-to-end training of two tasks versus training in isolation. Experimental results show the effectiveness of our text-based approach achieving an accuracy of 90% on classification task and an F1 of 75.82, 86.01, 61.63 on groups discussed above respectively, outperforming segmentation baselines. Further we show our framework achieves state of the results for table structure recognition on ICDAR 2013 dataset.
Anthology ID:
2020.emnlp-main.314
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3830–3840
Language:
URL:
https://aclanthology.org/2020.emnlp-main.314
DOI:
10.18653/v1/2020.emnlp-main.314
Bibkey:
Cite (ACL):
Milan Aggarwal, Hiresh Gupta, Mausoom Sarkar, and Balaji Krishnamurthy. 2020. Form2Seq : A Framework for Higher-Order Form Structure Extraction. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3830–3840, Online. Association for Computational Linguistics.
Cite (Informal):
Form2Seq : A Framework for Higher-Order Form Structure Extraction (Aggarwal et al., EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/paclic-22-ingestion/2020.emnlp-main.314.pdf
Optional supplementary material:
 2020.emnlp-main.314.OptionalSupplementaryMaterial.zip
Video:
 https://slideslive.com/38939348
Code
 Form2Seq-Data/Dataset