Methods › Sequential › Sequence To Sequence Models

Sequence To Sequence Models

16 methods 3,175 papers tagged archive 2025-07-28

The archive attaches this collection's text per method and the copies differ: 2 distinct texts across 3 of the 16 methods here. All are shown, most-carried first (a tie goes to the text carrying Papers with Code's collection boilerplate, then to the longer text); no vote is taken between them.

Text 1, carried by 2 of 16 methods:

Transformers are a type of neural network architecture that have several properties that make them effective for modeling data with long-range dependencies. They generally feature a combination of multi-headed attention mechanisms, residual connections, layer normalization, feedforward connections, and positional embeddings.

Text 2, carried by 1 of 16 methods:

Language Models are models for predicting the next word or character in a document. Below you can find a continuously updating list of language models.

Methods

All 16 methods in this collection, most-tagged first. Year is the archive's introduced_year; the archive stores 2000 when it has none, shown here as “–”. Papers counts distinct papers the archive tags with the method. Click a heading to sort.

BART – 1,642
T5 – 708
Seq2Seq Sequence to Sequence – 700
Pointer Network – 105
Tacotron – 65
GTS Goal-Driven Tree-Structured Neural Model – 46
ESIM Enhanced Sequential Inference Model – 15
ClariNet – 7
Graph2Tree Graph-to-Tree MWP Solver – 4
HBMP Hierarchical BiLSTM Max Pooling – 3
GAN-TTS – 2
ResBiLSTM Residual Bidirectional Long Short-Term Memory – 2
Cyclic Transformer – 1
LayoutReader – 1
WaveTTS – 1
mBARTHez – 1