pointer_summarizer
pointer_summarizer copied to clipboard
atulkum
pytorch implementation of "Get To The Point: Summarization with Pointer-Generator Networks"
I was successfully able to run the LSTM based pointer generator. While running the transformer_encoder branch with LSTM=false, I encounter this error: ``` File "training_ptr_gen/train.py", line 400, in train_processor.trainIters(config.max_iterations, args.model_file_path)...
https://github.com/atulkum/pointer_summarizer/blob/83e6a2e11beded743c8932bd97d5cc2d7f81c6d9/training_ptr_gen/train.py#L90 Will there be duplicated computation with LSTM? e.g. given an input [w1, w2, w3, w4, ... , wn], all the prefixes will be decoded by LSTM. Why not using...
Hello, Thanks for your valuable code. I have a question. When I run the code for 500k iterations. I get the rouge result: ROUGE-1: rouge_1_f_score: 0.2648 with confidence interval (0.2574,...
Hello, In the training process, we save one model every 5000 iterations. Besides training loss, are there any criteria to help choose the best model? Because I think even if...
hi, first of all thanks for your pytorch implementation. i m getting a pretty good results when i put is_coverage=False in config. But while putting it true all the summaries...
Hi, I hope you are doing well. While going through your implementation on the pointer generator, I have noticed that there's a difference in the implementation of the `p_gen` calculation...
I have trained model for chinese weibo data ,how could i predict single line?
Need help for retraining and cross validation and see if the ROUGE score matches exactly (or better) with the numbers reported in the paper. I just train for 500k iteration...
I'm using the same hypers but seeing this for my training curve. Why would this happen? Looks like the LR is too high but your curve with the same lr...
This commit implements a fully-automated development setup using Gitpod.io, an online IDE for GitHub and GitLab that enables Dev-Environments-As-Code. This makes it easy for anyone to get a ready-to-code workspace...
