Sequence to Sequence Learning with Neural Networks
Sequence-to-sequence learning uses an encoder and decoder to map variable-length input sequences to output sequences. The reported system uses multilayer LSTMs and reverses source sentences to improve optimization.
Overview. Sequence-to-sequence learning uses an encoder and decoder to map variable-length input sequences to output sequences.
Context. The reported system uses multilayer LSTMs and reverses source sentences to improve optimization.
Claims and evidence
Claim ledger, 2Sequence-to-sequence learning uses an encoder and decoder to map variable-length input sequences to output sequences.
The reported system uses multilayer LSTMs and reverses source sentences to improve optimization.