SDGCN
SDGCN copied to clipboard
Pinlong-Zhao
Modeling Sentiment Dependencies with Graph Convolutional Networks for Aspect-level Sentiment Classification
Thank you very much for your work. I am very interested in why you did not fine tune the BERT in the model SDGCN, but instead use the BERT Embedding?...
既然使用bert进行词向量表示，为什么在run_BERT.py文件中还要使用glove的词向量文件呢，也就是这句话：word_id_mapping, w2v = data_helpers.load_w2v(FLAGS.embedding_file_path, 300)，请您解惑一下
Metadata
Owner
Metadata
Modeling Sentiment Dependencies with Graph Convolutional Networks for Aspect-level Sentiment Classification