资源介绍
自然语言处理算法的Tensorflow实现
1. Seq2Seq(机器翻译)
encoder: LSTM
decorder: LSTM with beam search
dataset: Eng-french translation dataset
2.参加并说出(图片字幕)
encoder: Convnet-VGG
attention model: Bahdanua Attention
decoder: LSTM with beam search
dataset: COCO
3.情绪分析
encoder: multilayer LSTM
decoder: Classification Dense Layer
dataset: Imdb-dataset
4.加载预训练的单词嵌入
facebook: multilingual embeddings: MUSE
stanfor