The DOI matches its Crossref record; 65 of the 67 references it cites were found in a registry or an index.
Transformer-XL: Attentive Language Models beyond a Fixed-Length Context
Open accessAbstract
Transformers have a potential of learning longer-term dependency, but are limited by a fixed-length context in the setting of language modeling.We propose a novel neural architecture Transformer-XL that enables learning dependency beyond a fixed length without disrupting temporal coherence.It consists of a segment-level recurrence mechanism and a novel positional encoding scheme.Our method not only enables capturing longer-term dependency, but also resolves the context fragmentation problem.As a result, Transformer-XL learns dependency that is 80% longer than RNNs and 450% longer than vanilla Transformers, achieves better performance on both short and long sequences, and is up to 1,800+ times faster than vanilla Transformers during evaluation.Notably, we improve the state-ofthe-art results of bpc/perplexity to 0.99 on en-wiki8, 1.08 on text8, 18.3 on WikiText-103, 21.8 on One Billion Word, and 54.5 on Penn Treebank (without finetuning).When trained only on WikiText-103, Transformer-XL manages to generate reasonably coherent, novel text articles with thousands of tokens.Our code, pretrained models, and hyperparameters are available in both Tensorflow and PyTorch 1 .
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source doesn’t support the claim as written.
In the citing paper
“note that the Transformer XL model25 incorporates some form of recurrent processing within the transformer block, but it still takes the entire text as its input in parallel.”
From Incremental accumulation of linguistic context in artificial and biological neural networks (2025) · cites this paper as [25]
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Directly extending the context length of transformers incurs a quadratic increase in computational time and memory cost due to the transformer architecture's self-attention mechanism, making the design of new long-context architectures a pressing research challenge (Dai et al., 2019; Kitaev et al., 2020; Beltagy et al., 2020).”
From MemGPT: Towards LLMs as Operating Systems (2023) · cites this paper as Dai et al., 2019
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“We believe that the different trends are caused by the truncation problem [59], [60].”
From What Makes Good In-Context Demonstrations for Code Intelligence Tasks with LLMs? (2023) · cites this paper as [59]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Fixed-window methods : including context windows of 4K, 8K, and 16K tokens with FIFO eviction [10, 2]”
From FadeMem: Biologically-Inspired Forgetting for Efficient Agent Memory (2026) · cites this paper as [10]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Thus, in practice, Transformer-XL and Compressive Transformer need huge memory size to achieve good performance.”
From Memformer: a memory-augmented transformer for sequence modeling (2020) · cites this paper as Dai et al., 2019
Experimental — accuracy not yet measured
12 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 7×
“On the other hand, the direct connections between long-distance word pairs baked in attention mechanisms might ease optimization and enable the learning of long-term dependency (Bahdanau et al., 2014; Vaswani et al., 2017).”
BackgroundMethodInfluentialHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 2×
“Recurrent neural networks (RNNs), in particular Long Short-Term Memory (LSTM) networks (Hochreiter & Schmidhuber, 1997), have been a standard solution to language modeling and obtained strong results on multiple benchmarks.”
BackgroundExploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173 · cited 4×
“Second, though it is possible to use padding to respect the sentence or other semantic boundaries, in practice it has been standard practice to simply chunk long text into fixed-length segments due to improved efficiency (Peters et al., 2018; Devlin et al., 2018; Al-Rfou et al., 2018).”
BackgroundInfluentialBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 4×
“Second, though it is possible to use padding to respect the sentence or other semantic boundaries, in practice it has been standard practice to simply chunk long text into fixed-length segments due to improved efficiency (Peters et al., 2018; Devlin et al., 2018; Al-Rfou et al., 2018).”
BackgroundInfluentialNeural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213 · cited 2×
“On the other hand, the direct connections between long-distance word pairs baked in attention mechanisms might ease optimization and enable the learning of long-term dependency (Bahdanau et al., 2014; Vaswani et al., 2017).”
BackgroundDeep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983 · cited 4×
“Second, though it is possible to use padding to respect the sentence or other semantic boundaries, in practice it has been standard practice to simply chunk long text into fixed-length segments due to improved efficiency (Peters et al., 2018; Devlin et al., 2018; Al-Rfou et al., 2018).”
BackgroundInfluentialRecurrent neural network based language model
Mikolov, T., Karafiát, M., Burget, L., Černocký, J., & Khudanpur, S. (2010) · Interspeech 2010 · doi:10.21437/interspeech.2010-343 · Cited by 5,390 · cited 5×
“However, different from truncated BPTT, our method caches a sequence of hidden states instead of the last one, and should be applied together with the relative positional encoding technique described in Section 3.3.”
BackgroundMethodInfluentialAn Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
Bai, S., Kolter, J. Z., & Koltun, V. (2018) · arXiv · doi:10.48550/arxiv.1803.01271 · Cited by 4,655
Neural Architecture Search with Reinforcement Learning
Zoph, B., & Le, Q. V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01578 · Cited by 3,974
Self-citation
Research works printed but not linked: 1
- Matthew E Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep contextualized word rep- resentations. arXiv preprint arXiv:1802.05365. · arXiv
Cited by
Transformers: State-of-the-Art Natural Language Processing
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2020.emnlp-demos.6 · Cited by 8,741
“, 2019) Trans-XL (Dai et al., 2019) XLNet (Yang et al.”
Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, J., Xiong, H., & Zhang, W. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i12.17325 · Cited by 7,752
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
Zheng, S., Lu, J., Zhao, H., Zhu, X., Luo, Z., Wang, Y., Fu, Y., Feng, J., Xiang, T., Torr, P. H. S., et al. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00681 · Cited by 4,008
A review on the attention mechanism of deep learning
Niu, Z., Zhong, G., & Yu, H. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.03.091 · Cited by 3,379
Conformer: Convolution-augmented Transformer for Speech Recognition
Gulati, A., Qin, J., Chiu, C.-C., Parmar, N., Zhang, Y., Yu, J., Han, W., Wang, S., Zhang, Z., Wu, Y., et al. (2020) · Interspeech 2020 · doi:10.21437/interspeech.2020-3015 · Cited by 3,150
Metadata
- Authors
- Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q., & Salakhutdinov, R.
- Affiliations
- Carnegie Mellon University (US)
- Google (United States) (US)
- Venue
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Published
- 2019
- Pages
- 2978-2988
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W2964110616
- Cited by
- 3,169
- References
- 67
- Citations by year
- 2026: 163 · 2025: 361 · 2024: 434 · 2023: 585 · 2022: 504 · 2021: 612 · 2020: 403 · 2019: 107
- FWCI
- 155.55
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- Funders
- National Science Foundation (1546329, 1763562)
- U.S. Department of Energy
- Nvidia
- Office of Science
- Office of Naval Research (N000141812861)
- Advanced Scientific Computing Research
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Keywords
- Transformer-XL, long-range dependencies, positional encoding, language modeling, temporal coherence, sequence generation, pre-trained language models
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Transformer-XL: Attentive Language Models beyond a Fixed-Length Context. https://app.cochat.ai/papers/10.18653/v1/p19-1285
- The paper
- Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q., & Salakhutdinov, R. (2019). Transformer-XL: Attentive Language Models beyond a Fixed-Length Context. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. https://doi.org/10.18653/v1/p19-1285
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.