推荐github上的一个NLP代码实现的教程:nlp-tutorial,一个使用TensorFlow和Pytorch学习NLP(自然语言处理)的教程,教程中的大多数NLP模型都使用少于100行代码实现。
教程说明
这是使用TensorFlow和Pytorch学习NLP(自然语言处理)的教程,把常用NLP模型用不到100行的代码实现了,教程里附论文下载,并且包含py和ipynb文件,经过测试全部通过。
仓库地址:
https://github.com/graykode/nlp-tutorial
里面有使用说明和样例(py和ipynb格式)。
教程目录
1. Basic Embedding Model(基础嵌入模型)
1-1. NNLM(Neural Network Language Model)– Predict Next Word
- 论文下载
A Neural Probabilistic Language Model(2003)
- 代码实现
NNLM_Tensor.ipynb, NNLM_Torch.ipynb
1-2. Word2Vec(Skip-gram) – EmbeddingWords and Show Graph
- 论文下载
Distributed Representations of Words and Phrases and their Compositionality(2013)
- 代码实现
Word2Vec_Tensor(NCE_loss).ipynb, Word2Vec_Tensor(Softmax).ipynb, Word2Vec_Torch(Softmax).ipynb
1-3. FastText(Application Level)- Sentence Classification
- 论文下载
Bag of Tricks for Efficient Text Classification(2016)
- 代码实现
2. CNN(卷积神经网络)
2-1. TextCNN – BinarySentiment Classification
- 论文下载
Convolutional Neural Networks for Sentence Classification(2014)
- 代码实现
TextCNN_Tensor.ipynb, TextCNN_Torch.ipynb
2-2. DCNN(Dynamic Convolutional Neural Network)
3. RNN(循环神经网络)
3-1. TextRNN – Predict NextStep
- 论文下载
Finding Structure in Time(1990)
- 代码实现
TextRNN_Tensor.ipynb, TextRNN_Torch.ipynb
3-2. TextLSTM – Autocomplete
- 论文下载
- 代码实现
TextLSTM_Tensor.ipynb, TextLSTM_Torch.ipynb
3-3. Bi-LSTM – Predict NextWord in Long Sentence
- 代码实现
Bi_LSTM_Tensor.ipynb, Bi_LSTM_Torch.ipynb
4. Attention Mechanism(注意力机制)
4-1. Seq2Seq – Change Word
- 论文下载
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation(2014)
- 代码实现
Seq2Seq_Tensor.ipynb, Seq2Seq_Torch.ipynb
4-2. Seq2Seq with Attention – Translate
- 论文下载
Neural Machine Translation by Jointly Learning to Align and Translate(2014)
- 代码实现
Seq2Seq(Attention)_Tensor.ipynb, Seq2Seq(Attention)_Torch.ipynb
4-3. Bi-LSTM with Attention – BinarySentiment Classification
- 代码实现
Bi_LSTM(Attention)_Tensor.ipynb, Bi_LSTM(Attention)_Torch.ipynb
5. Model based on Transformer(Transformer模型)
5-1. The Transformer – Translate
- 论文下载
Attention Is All You Need(2017)
- 代码实现
Transformer_Torch.ipynb, Transformer(Greedy_decoder)_Torch.ipynb
5-2. BERT – ClassificationNext Sentence & Predict Masked Tokens
- 论文下载
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding(2018)
- 代码实现
BERT_Torch.ipynb
部分内容截图
TextCNN的两种实现方式(使用TensorFlow和Pytorch)
总结
推荐github上的一个NLP代码教程:nlp-tutorial,一个使用TensorFlow和Pytorch学习NLP(自然语言处理)的教程,教程中的大多数NLP模型都使用少于100行代码实现。
仓库地址:
https://github.com/graykode/nlp-tutorial
里面有使用说明和样例(py和ipynb格式)。
仓库作者:Tae Hwan Jung(Jeff Jung)