PreSumm
PreSumm copied to clipboard
nlpyang
code for EMNLP 2019 paper Text Summarization with Pretrained Encoders
In the "create_batches" of class DataIterator ____________ _for buffer in self.batch_buffer(data, self.batch_size * 300):_ ____________ why 300? I do think the second para should be **_self.batch_size * self.args.max_pos_**, otherwise the...
Hello, Are the batch sizes and accum count for the bert large exactly the same as the base model? I have been trying to get the results but my bert...
I use validate mode to get my model performance, but I didn't see ROUGE scores, I just saw : [2021-02-19 07:28:44,643 INFO] * number of parameters: 180222522 [2021-02-19 07:41:53,946 INFO]...
Hi folks, I want to use these pre-trained models for summarization with my custom input text. Let's say, I have 10 articles that I want to summarize using BertSumExt, so...
Hello, I was using PreSumm code to run on a custom dataset. I made the format of data compatible with model input. I trained Transformer baseline, a simple encoder and...
Could you clear to what should the Step 4. Format to Simpler Json Files do . my case : i have my own data-set . i am trying to apply...
Hi @nlpyang , can you give me some suggestion on how to resume the previous checkpoint model for continuous training without having to train the model from beginning at different...
getting the below error while trying to run pyrouge to calculate ROUGE on colab  The above error is obtained at PreSumm/src/others/pyrouge.py", line 453, in __get_rouge_home_dir_from_settings with open(self._settings_file) as f:
I am trying to load a pretrained model in my notebook. Using google colab for the experiment, import torch PATH = "path/to/the/model/model_step_148000.pt" model = torch.load(PATH) it gives me this error...
File "train.py", line 122, in train_abs(args, device_id) File "E:\project\PreSumm\src\train_abstractive.py", line 273, in train_abs train_abs_single(args, device_id) File "E:\project\PreSumm\src\train_abstractive.py", line 334, in train_abs_single trainer.train(train_iter_fct, args.train_steps) File "E:\project\PreSumm\src\models\trainer.py", line 133, in train train_iter...
