- Task 1 - E2E Complex Entity Linking
- Task 2 - E2E Complex Entity Labeling
- Task 3 - E2E Zero-shot Structured Text Extraction
- Task 4 - E2E Few-shot Structured Text Extraction
method: LayoutLMv3&StrucText2023-03-24
Authors: Mei Jiang(姜媚),Minhui Wu(伍敏慧),Chen Li(李琛),Jing Lv(吕静),Haoxi Li(李昊曦),Lifu Wang(王立夫),Sicong Liu(刘思聪)
Affiliation: TencentOCR
Description: Based on a large pretrained model and LayoutLMv3 and StrucText architecture, with some pre/post processing methods.
method: LayoutLMv3&StrucText2023-03-24
Authors: Mei Jiang(姜媚),Minhui Wu(伍敏慧),Chen Li(李琛),Jing Lv(吕静),Haoxi Li(李昊曦),Lifu Wang(王立夫),Sicong Liu(刘思聪)
Affiliation: TencentOCR
Description: Based on a large pretrained model and LayoutLMv3 and StrucText architecture, with some pre/post processing methods.
method: Fewshot-brain_v12023-03-24
Authors: Boqian Xia, Yu Wang, Yadong Li, Hongbin Wang
Affiliation: Ant Group
Email: xiaboqian.xbq@antgroup.com, yuwangtj@yeah.net
Description: An ensemble of end to end models for few shot information extraction.This model does not rely on external OCR, and the architecture is concise
| Date | Method | score | score1 | score2 | |||
|---|---|---|---|---|---|---|---|
| 2023-03-24 | LayoutLMv3&StrucText | 84.43% | 87.14% | 73.59% | |||
| 2023-03-24 | LayoutLMv3&StrucText | 82.51% | 85.15% | 71.93% | |||
| 2023-03-24 | Fewshot-brain_v1 | 74.39% | 77.81% | 60.71% | |||
| 2023-03-24 | Dao Xianghu light of TianQuan | 68.19% | 71.48% | 55.03% | |||
| 2023-03-25 | Task4_gpt | 0.00% | 0.00% | 0.00% |