Artidoro Pagnoni

Punctuation not consistent for M19 (Text Summarization with Pretrained Encoders)

3

It appears that there are no periods at the end of summaries (and possibly also sentences) in the outputs of `bertsumextabs`. Is this a feature of the model? Could this...

Error when running the template TorchTensorType.tt

1

When you right click and Run Custom Tool, it should generate the .cs file. If it is not currently set up to do so, could can delete the .tt file...

Hello, I have two questions on your data and on OpenIE more generally. 1. I am wondering if a sentence which only has the verb "to be" should be considered...

Where is the finetune_pt_squad.py file?

9

I have a hard time understanding how to generate the answers given the questions.

Adding new tokens causes performance and memory issues

4

Bug description: - Adding new tokens to the tokenizer and corresponding embeddings causes the embeddings to be finetuned (`requires_grad = True` after `resize_token_embeddings()` is called). - The embeddings are updated...

Data preprocessing details

4

Could you give more details on how you preprocess the data? I noticed underscore characters are present instead of some special characters, for example. It would be ideal if you...