[LayoutLM] Do you plan to open source the receipt understanding task example for the SROIE dataset?

[oni-on]

It'd be awesome to be able to reproduce the results obtained on the SROIE challenge.

[jackie930]

feeling the same.

[ruifcruz]

same here. I am getting very different results from the ones presented in the paper..!

[ruifcruz]

Mabe it helps: https://github.com/ruifcruz/sroie-on-layoutlm

[oni-on]

Great work @ruifcruz ! I'm trying to run your notebook atm.

[SuryaThiru]

Mabe it helps: https://github.com/ruifcruz/sroie-on-layoutlm

I see, that this notebook directly uses the OCR annotations provided with the original dataset. Do we know what OCR engine was used by the original authors for the SROIE information extraction task? The LayoutLMv2 paper mentions that they "use the official OCR annotations ". Does that mean no OCR was performed and the annotations were directly used?

[ruifcruz]

As far as I remember (some time have passed since then), they have used tesseract (in v1). I would say that they didn't need to OCR because they already had the annotations from the contest.