Sequence To Sequence Models
Sequence to Sequence
Introduced by Sutskever et al. in Sequence to Sequence Learning with Neural NetworksSeq2Seq, or Sequence To Sequence, is a model used in sequence prediction tasks, such as language modelling and machine translation. The idea is to use one LSTM, the encoder, to read the input sequence one timestep at a time, to obtain a large fixed dimensional vector representation (a context vector), and then to use another LSTM, the decoder, to extract the output sequence from that vector. The second LSTM is essentially a recurrent neural network language model except that it is conditioned on the input sequence.
(Note that this page refers to the original seq2seq not general sequence-to-sequence models)
Source: Sequence to Sequence Learning with Neural Networks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Decoder | 82 | 6.83% |
| Sentence | 69 | 5.75% |
| Machine Translation | 63 | 5.25% |
| Translation | 58 | 4.83% |
| Language Modelling | 44 | 3.67% |
| Text Generation | 42 | 3.50% |
| Semantic Parsing | 42 | 3.50% |
| Language Modeling | 34 | 2.83% |
| Speech Recognition | 23 | 1.92% |
LSTM
