Methods › Natural Language Processing › Autoregressive Transformers › Transformer-XL

Transformer-XL

64 papers tagged archive 2025-07-28

Introduced by Zihang Dai et al. in Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context

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

Transformer-XL (meaning extra long) is a Transformer architecture that introduces the notion of recurrence to the deep self-attention network. Instead of computing the hidden states from scratch for each new segment, Transformer-XL reuses the hidden states obtained in previous segments. The reused hidden states serve as memory for the current segment, which builds up a recurrent connection between the segments. As a result, modeling very long-term dependency becomes possible because information can be propagated through the recurrent connections. As an additional contribution, the Transformer-XL uses a new relative positional encoding formulation that generalizes to attention lengths longer than the one observed during training.

PaperSource

Papers archive 2025-07-28

30 shown of 64, 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 86 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
Language Modelling38
Language Modeling27
Decoder7
Machine Translation6
Speech Recognition5
Translation5
speech-recognition5
Text Generation4
Automatic Speech Recognition3
Automatic Speech Recognition (ASR)3
Paraphrase Identification3
Reinforcement Learning (RL)3
Sentence3
Word Embeddings3
Abstractive Text Summarization2
Deep Attention2
Deep Reinforcement Learning2
GPU2
Graph Neural Network2
Music Generation2

Usage over time archive 2025-07-28

Papers per year tagged with Transformer-XL: 2019 to 2025, peak 16 16 0 2019: 13 papers 2019 2020: 16 papers 2020 2021: 14 papers 2021 2022: 6 papers 2022 2023: 10 papers 2023 2024: 4 papers 2024 2025: 1 paper 2025
Papers per year the archive tags with this method, by the paper's archive date (64 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

Autoregressive TransformersTransformers

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