How to summarize a text using pre-trained models?

[yasersakkaf]

Hello, I have a text of about 70-80 words in a .txt file. I want to summarize it using the pre-trained model. Please guide me stepwise how to do. It is difficult for me to understand due all the complex parameters and as I am getting started at this.

[landmann]

Hey! Coincidentally, someone already asked this question here.

You need to first process your own .txt file using the instructions here and then use the pre-trained model as explained here

[fahimeh62]

Hi @yasersakkaf

Did you find the solution for your question? I followed the discussion in other issue as well, but I still needs to know how can I use the pretrained model to finetune on my dataset. I also need to know how should I prepare the binary files from my data which is in form of text files. Any help appreciated! Thanks.

[yasersakkaf]

I am afraid the ANSWER IS NO. But I found some other repo which may be helpful for you too. please use the link below https://github.com/Currie32/Text-Summarization-with-Amazon-Reviews

[landmann]

Hi All, do not fret! I'll clean up my code and post it within the end of this or next week. I was able to use my own dataset and do both: train a model from scratch and also use the pre-trained model.

As an added bonus, I implemented the GloVe embeddings as well ;)

Stay tuned!

[fahimeh62]

Thanks @yasersakkaf @landmann Great! I'll be await of update.

[yasersakkaf]

@landmann: Good. I will wait for the update then.

[dondon2475848]

If you want to convert your own data(.txt) to binary data (.bin)

You can clone below repository: https://github.com/dondon2475848/make_datafiles_for_pgn

Run:

python make_datafiles.py  ./stories  ./output

It processes your test data into the binary format .

[Sabyasachi18]

@landmann ...Hi Landmann, Can you tell how you used the pre-trained model and fine tuned the pre-trained model? It would be very helpful for me. Thanks in advance!