</> Code with Papers by Syntology

Methods › Natural Language Processing › Machine Translation Models › Seq2Seq

Sequence to Sequence

Seq2Seq

700 papers tagged archive 2025-07-28

Introduced by Ilya Sutskever et al. in Sequence to Sequence Learning with Neural Networks

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

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)

PaperSource

Papers archive 2025-07-28

30 shown of 700, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 453 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Machine Translation114
Decoder111
Translation107
Sentence96
Text Generation63
Language Modelling61
Language Modeling50
Semantic Parsing50
Speech Recognition34
speech-recognition33
Abstractive Text Summarization32
Question Answering31
Text Summarization30
Diversity24
Retrieval24
Response Generation22
Reinforcement Learning20
Data Augmentation19
Grammatical Error Correction18
NMT18

Usage over time archive 2025-07-28

Papers per year tagged with Seq2Seq: 2014 to 2025, peak 116 116 0 2014: 1 paper 2014 2015: 1 paper 2015 2016: 11 papers 2016 2017: 24 papers 2017 2018: 78 papers 2018 2019: 108 papers 2019 2020: 104 papers 2020 2021: 116 papers 2021 2022: 103 papers 2022 2023: 89 papers 2023 2024: 52 papers 2024 2025: 13 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (700 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Machine Translation ModelsSequence To Sequence Models

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections