Sequence-to-Sequence Models

Coming Soon

This example is planned for a future release. Check back for updates on seq2seq implementations.

Overview

This example will demonstrate:

• Encoder-decoder architectures
• Attention mechanisms
• Machine translation
• Text summarization

Planned Features

• Transformer encoder-decoder
• Cross-attention layers
• Beam search decoding
• Teacher forcing training

Related Documentation

• Transformer Text
• Text Compression
• Autoregressive Models

References

• Sutskever et al., "Sequence to Sequence Learning with Neural Networks" (2014)
• Bahdanau et al., "Neural Machine Translation by Jointly Learning to Align and Translate" (2015)