Seq2Seq, 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 NetworksPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Sentence | 72 | 6.97% |
Machine Translation | 66 | 6.39% |
Translation | 62 | 6.00% |
Text Generation | 46 | 4.45% |
Language Modelling | 45 | 4.36% |
Semantic Parsing | 40 | 3.87% |
Question Answering | 25 | 2.42% |
Abstractive Text Summarization | 21 | 2.03% |
Speech Recognition | 21 | 2.03% |