Victor Yang

Results 5 comments of Victor Yang

Fixed by setting `is_training` to False here: https://github.com/santhoshkolloju/Abstractive-Summarization-With-Transfer-Learning/blob/master/model.py#L32

Good results! So it is very close to the original paper, right? It means VDPWI-pytorch works! Btw, according to my experience, SGD + good `lr` is usually the best setup....

Result of Kim CNN (multichannel) on Subjectivity dataset [(Pang and Lee, 2004) ](https://www.cs.cornell.edu/people/pabo/movie-review-data/) with 10-fold CV: 92.9%, while original paper reports 93.2%.

Results of Kim CNN on SST-2 dataset | Setup | rand | static | non-static | Multichannel| | ------------- |:-------------:| -----:| -----:| -----:| | Original paper | 82.7 | 86.8...

@liudonglei You are right. Current SMCNN code needs refactoring. See https://github.com/castorini/Castor/issues/128. Welcome to create your PR to contribute!