Ehsan Hemmati

seed value

4

Hi, I have trained a classifier and I am trying to do inference for a text file rather than a single input. I realized that I will get a different...

A different discriminator?

5

Hi, I really enjoyed your paper. In this regard, I have following questions that I appreciate your reply, 1) I wonder if it possible to replace the current discriminator which...

Evaluation metrics per class for multilabel sequence classification

2

Hi, Does the repo support reporting evaluation metrics per class for multilabel sequence classification? Thanks

Suggestion for doing core for longer sequences?

1

Hi, First, thank you for providing this valuable resource. According to Table 4 of the Bert paper, for long sequences with length 1152+ the performance declined. I wonder if I...

Hi, I am trying to train a title-storyline to story model of plan and write paper using this command: ``` python pytorch_src/main.py --batch_size 20 --train-data rocstory_plan_write/ROCStories_all_merge_tokenize.titlesepkeysepstory.train --valid-data rocstory_plan_write/ROCStories_all_merge_tokenize.titlesepkeysepstory.dev --test-data rocstory_plan_write/ROCStories_all_merge_tokenize.titlesepkeysepstory.test...

Instruction to pretrain sentence compression model and prepare feature for new dataset

1

Hi, Thanks for the nice source. I want to train and run your method on a new dataset. I wonder if the repository contain code for pretrainig sentence compression module?...

Script Generation

1

Hi, Thanks for the nice work. I wonder if there is any code for Script generation using your event representation? In the paper, the representations were evaluated on script event...