Authors: Organizers

Affiliation: Rossum.ai, Czech Technical University in Prague, University of La Rochelle

Description: Baseline method. Uses multi-label NER formulation with RoBERTa base as the backbone. It is pre-trained on the synthetic part of the DocILE dataset.

Authors: Organizers

Affiliation: Rossum.ai, Czech Technical University in Prague, University of La Rochelle

Description: Baseline method. Uses multi-label NER formulation with LayoutLMv3 as the backbone. It is pre-trained on the unlabelled and synthetic parts of the DocILE dataset.

method: baseline - RoBERTa-base2023-05-02

Authors: Organizers

Affiliation: Rossum.ai, Czech Technical University in Prague, University of La Rochelle

Description: Baseline method. Uses multi-label NER formulation with RoBERTa base as the backbone.

Ranking Table

Description Paper Source Code
DateMethodF1APPrecisionRecall
2023-05-02baseline - RoBERTa-base with synthetic pre-training64.91%51.35%65.99%63.87%
2023-05-02baseline - LayoutLMv3 with unsupervised and synthetic pre-training64.54%52.38%66.30%62.86%
2023-05-02baseline - RoBERTa-base63.68%50.52%64.44%62.94%
2023-05-02baseline - LayoutLMv3 with unsupervised pre-training61.98%47.92%63.96%60.13%
2023-05-25GraphDoc+Classify+Merge61.78%38.32%65.76%58.25%

Ranking Graphic

Ranking Graphic