[NLP] Sentiment classification using LSTMs and torchtext

0. Statement. 🏫

Today I want to use LSTM to do sentiment classification on the IMDB dataset. 😇

1. Experimental field. 😊

I am deploying today’s experiment on colab because of the huge amount of LSTM operations.😭

2. Data pre-processing in NLP. 🤔

1. Import of text data.
2. Division of the text data set (training set, validation set, and testing set).
3. Word separation.
4. Construction of vocabulary.
5. Encoding and mapping of text data to vocabularies.
6. Generation of word vectors.
7. Generation of batch text data.

3. Intro torchtext. 🧐

Recommend this blog about torchtext.

4. Pre-processing of IMDB datasets.

⚠️: Filed -> splits -> build_vocab

import numpy as np
import torch
from torch import nn, optim
!pip install torch==1.8.0 torchtext==0.9.0
from torchtext.legacy import data, datasets

torch.manual_seed(1024)

!python -m spacy download en_core_web_md 
TEXT = data.Field(tokenize='spacy', tokenizer_language='en_core_web_md')
LABEL = data.LabelField(dtype=torch.float)

train_data, test_data = datasets.IMDB.splits(TEXT, LABEL)

print('len of train data:', len(train_data))        
print('len of test data:', len(test_data))          

print(train_data.examples[10].text)
print(train_data.examples[10].label)

TEXT.build_vocab(train_data, max_size=10000, vectors='glove.6B.100d')
LABEL.build_vocab(train_data)
print(len(TEXT.vocab))                     
print(TEXT.vocab.itos[:])                  
print(TEXT.vocab.stoi['here'])              
print(LABEL.vocab.stoi)      

batchsz = 30
train_iterator, test_iterator = data.BucketIterator.splits(
                                (train_data, test_data),
                                batch_size = batchsz,
                               )              

5. Construction of neural network.

class lstm(nn.Module):

    def __init__(self, vocab_size, embedding_dim, hidden_dim):

        super(lstm, self).__init__()


        self.embedding = nn.Embedding(vocab_size, embedding_dim)        

        self.rnn = nn.LSTM(embedding_dim, hidden_dim, num_layers=2,     
                           bidirectional=True, dropout=0.5)
        self.fc = nn.Linear(hidden_dim*2, 1)
        self.dropout = nn.Dropout(0.5)


    def forward(self, x):
    
        embedding = self.dropout(self.embedding(x))

        output, (hidden, cell) = self.rnn(embedding)          

        hidden = torch.cat([hidden[-2], hidden[-1]], dim=1)   
        hidden = self.dropout(hidden)
        out = self.fc(hidden)

        return out
lstm = lstm(len(TEXT.vocab), 100, 256)
print(lstm)

6. Updating the embedding layer with Glove’s parameters.

pretrained_embedding = TEXT.vocab.vectors
print('pretrained_embedding:', pretrained_embedding.shape)    
lstm.embedding.weight.data.copy_(pretrained_embedding)
print('embedding layer inited.')

7. Optimizer & criterion.

optimizer = optim.Adam(lstm.parameters(), lr=5e-2)
criterion = nn.BCEWithLogitsLoss() 

8. Construction of accuracy function.

def binary_acc(preds, y):
     preds = torch.round(torch.sigmoid(preds))
     correct = torch.eq(preds, y).float()
     acc = correct.sum() / len(correct)
     return acc

9. Training & testing

def train(lstm, iterator, optimizer, criterion):

    avg_acc = []
    lstm.train()        

    for i, batch in enumerate(iterator)
    
        pred = lstm(batch.text).squeeze(1)            

        loss = criterion(pred, batch.label)
        acc = binary_acc(pred, batch.label).item()   
        avg_acc.append(acc)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()                             
        print(i, acc)

    avg_acc = np.array(avg_acc).mean()
    print('avg acc:', avg_acc)

def evaluate(lstm, iterator, criterion):
    avg_acc = []
    lstm.eval()         

    with torch.no_grad():
        for batch in iterator:

            pred = lstm(batch.text).squeeze(1)      
            loss = criterion(pred, batch.label)
            acc = binary_acc(pred, batch.label).item()
            avg_acc.append(acc)

    avg_acc = np.array(avg_acc).mean()

    print('test acc:', avg_acc)
    
for epoch in range(5):
  train(lstm, train_iterator, optimizer, criterion)
  evaluate(lstm, test_iterator, criterion)

Finally 🤩

Thank you for the current age of knowledge sharing and the people willing to share it, thank you! The knowledge on this blog is what I’ve learned on this site, thanks for the support! 😇