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

lancopku / Skeleton-Based-Generation-Model

Code for "A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation" (EMNLP 2018)

65 stars 16 forks source link

Instruction to pretrain sentence compression model and prepare feature for new dataset #8

Open ehsan-soe opened 4 years ago

ehsan-soe commented 4 years ago

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? Also can you provide some instruction for preparing feature files to extract skeleton for new dataset?

Thanks

victorup commented 4 years ago

Hello, I'm reading this source now. Do you know how to build "train_sc.txt", if I just have the "train_process.txt"? Thank you!