Content Snapshot Code Missing

[waytehsu]

TaBERT/table_bert/vertical/input_formatter.py

Lines 82 to 83 in cf5351c

	if self.config.sample_row_num < row_num:
	sampled_row_ids = sorted(random.sample(row_ids, k=self.config.sample_row_num))

Thanks for open-sourcing the project. In the paper, you describe Content Snapshot as using n-gram to select the top K-rows. Do you have the code of that part in the repo? I see in your current implementation, you simply randomly choose K-rows for training instead, as shown in the snippet above.

[pafitis]

Hi — thanks for publishing this!

I was wondering if you are planning to add the content snapshot code.

Thanks for your time; very cool stuff!!