Methods › General › Deep Tabular Learning › BiLSTM

Bidirectional LSTM

BiLSTM

introduced 2001 657 papers tagged archive 2025-07-28

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

A Bidirectional LSTM, or biLSTM, is a sequence processing model that consists of two LSTMs: one taking the input in a forward direction, and the other in a backwards direction. BiLSTMs effectively increase the amount of information available to the network, improving the context available to the algorithm (e.g. knowing what words immediately follow and precede a word in a sentence).

Image Source: Modelling Radiological Language with Bidirectional Long Short-Term Memory Networks, Cornegruta et al

Code snippet in the archive: a link on www.ebi.ac.uk (archive link, not checked and not linked: not a code host this site links to).

Papers archive 2025-07-28

30 shown of 657, 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 449 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
Word Embeddings99
Sentence98
Sentiment Analysis64
Language Modelling52
Named Entity Recognition (NER)50
Language Modeling48
General Classification47
Named Entity Recognition43
named-entity-recognition43
Text Classification41
NER39
Transfer Learning36
text-classification34
Classification30
Question Answering30
Dependency Parsing22
Natural Language Inference22
POS22
Machine Translation21
Decoder19

Usage over time archive 2025-07-28

Papers per year tagged with BiLSTM: 2015 to 2025, peak 161 161 0 2015: 1 paper 2015 2016: 4 papers 2016 2017: 11 papers 2017 2018: 69 papers 2018 2019: 161 papers 2019 2020: 136 papers 2020 2021: 106 papers 2021 2022: 41 papers 2022 2023: 47 papers 2023 2024: 46 papers 2024 2025: 35 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (657 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

Deep Tabular Learning

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