Recurrent neural networks for text classification

Deep Learning for Text with PyTorch

Shubham Jain

Data Scientist

RNNs for text

Handle sequences of varying lengths
Maintain an internal short-term memory
CNNs spot patterns in chunks
RNNs remember past words for greater meaning

RNNs for text classification

Sarcasm Image

Why?

RNNs can read sentences like humans, one word at a time
Understand context and order

Example: Detecting sarcasm in a tweet

"I just love getting stuck in traffic."

Sarcastic

Recap: Implementing Dataset and DataLoader

# Import libraries
from torch.utils.data import Dataset, DataLoader

# Create a class
class TextDataset(Dataset):

    def __init__(self, text):
        self.text = text

    def __len__(self):
        return len(self.text)

    def __getitem__(self, idx):
        return self.text[idx]

RNN implementation

sample_tweet = "This movie had a great plot and amazing acting."
# Preprocess the review and convert it to a tensor (not shown for brevity)
# ...
sentiment_prediction = model(sample_tweet_tensor)

Train an RNN model to classify tweet as positive or negative
Output: "Positive"

RNN variation: LSTM

Sentiment Analysis Image

Tweet:

  "Loved the cinematography, 
  hated the dialogue. 
  The acting was exceptional,
  but the plot fell flat."

Long Short Term Memory (LSTM) can capture complexities where RNNs may struggle

LSTM

LSTM architecture: Input gate, forget gate, and output gate

class LSTMModel(nn.Module):

    def __init__(self, input_size, hidden_size, output_size):
        super(LSTMModel, self).__init__()
        self.lstm = nn.LSTM(input_size, hidden_size, batch_first=True)
        self.fc = nn.Linear(hidden_size, output_size)


    def forward(self, x):
        _, (hidden, _) = self.lstm(x)
        output = self.fc(hidden.squeeze(0))
        return output

RNN variation: GRU

Email subject:

   "Congratulations!
    You've won a free trip 
    to Hawaii!"

Gated Recurrent Unit (GRU) can quickly recognize spammy patterns without needing the full context

Email spam

GRU

class GRUModel(nn.Module):
    def __init__(self, input_size, hidden_size, output_size):
        super(GRUModel, self).__init__()
        self.gru = nn.GRU(input_size, hidden_size, batch_first=True)
        self.fc = nn.Linear(hidden_size, output_size)

    def forward(self, x):
        _, hidden = self.gru(x)
        output = self.fc(hidden.squeeze(0))
        return output

Let's practice!

Deep Learning for Text with PyTorch