nlpyang / PreSumm

code for EMNLP 2019 paper Text Summarization with Pretrained Encoders
MIT License
1.29k stars 465 forks source link

Getting the same sequence for all input candidate in generation #242

Open samanenayati opened 2 years ago

samanenayati commented 2 years ago

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 decoder, and stopped training when perplexity was low, around 2. However, in the inference, I get a very low rouge score. When I checked the actual generated candidates, I saw for all the inputs, the model generates the same candidate. I could not figure out the issue. Any help is greatly appreciated.