Version 1.1.1

• Optimize Dataset and DataLoader
• Sort vocabulary for reproducibility when setting seed

Version 1.1

• Add new models: MVLSTM, MatchPyramid, HBMP, DUET, MatchSRNN, aNMM and DIIN
• Add activation to classification models
• Add Ngram callbacks for Dataset
• Remove DSSMPreprocessor, CDSSMPreprocessor and CDSSMPadding
• Add BERT attention_mask and token_type_ids
• Support specifying GPUs for DataParallel and remove parameter data_parallel in trainer
• Fix other bugs

Version 1.0

• Written based on PyTorch
• Add BertPreprocessor, BertPadding, BertModule and Bert model
• Speed up loading embedding & support word2vec, GloVe and fastText
• Implement a majority of matching models
• Support dynamic padding
• Auto check task when defining a task
• Support multiprocess DataLoader
• Support early stopping, clipping gradient norm, validation interval and auto save best model