Fully Quantized Transformer for Machine Translation
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
State-of-the-art neural machine translation methods employ massive amounts of parameters.Drastically reducing computational costs of such methods without affecting performance has been up to this point unsuccessful.To this end, we propose FullyQT: an allinclusive quantization strategy for the Transformer.To the best of our knowledge, we are the first to show that it is possible to avoid any loss in translation quality with a fully quantized Transformer.Indeed, compared to fullprecision, our 8-bit models score greater or equal BLEU on most tasks.Comparing ourselves to all previously proposed methods, we achieve state-of-the-art quantization results.
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.
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
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
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
BERT: 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
XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
Rastegari, M., Ordonez, V., Redmon, J., & Farhadi, A. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_32 · Cited by 4,408
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., Adam, H., & Kalenichenko, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00286 · Cited by 4,114
Learning Efficient Convolutional Networks through Network Slimming
Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., & Zhang, C. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.298 · Cited by 2,761
Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., & Bengio, Y. (2016) · arXiv · doi:10.48550/arxiv.1602.02830 · Cited by 2,106
A Structured Self-attentive Sentence Embedding
Lin, Z., Feng, M., Santos, C. N. D., Yu, M., Xiang, B., Zhou, B., & Bengio, Y. (2017) · arXiv · doi:10.48550/arxiv.1703.03130 · Cited by 1,743 · cited 1×
“A few variations to this additive attention mechanism have been proposed, such as multiplicative and self-attention (Luong et al., 2015; Cheng et al., 2016; Lin et al., 2017).”
BackgroundDoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
Zhou, S., Wu, Y., Ni, Z., Zhou, X., Wen, H., & Zou, Y. (2016) · arXiv · doi:10.48550/arxiv.1606.06160 · Cited by 1,690
Cited by
Han (2023) · doi:10.1109/tpami.2022.3152247 · Cited by 4,682
PTQ4ViT: Post-Training Quantization for Vision Transformers with Twin Uniform Quantization
Yuan, Z., Xue, C., Chen, Y., Wu, Q., & Sun, G. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19775-8_12 · Cited by 163
“QAT can be used to quantize transformers [18].”
BackgroundSoftermax: Hardware/Software Co-Design of an Efficient Softmax for Transformers
Stevens, J. R., Venkatesan, R., Dai, S., Khailany, B., & Raghunathan, A. (2021) · 2021 58th ACM/IEEE Design Automation Conference (DAC) · doi:10.1109/dac18074.2021.9586134 · Cited by 148
HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers
Dong, P., Sun, M., Lu, A., Xie, Y., Liu, K., Kong, Z., Meng, X., Li, Z., Lin, X., Fang, Z., et al. (2023) · 2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca56546.2023.10071047 · Cited by 128
“(ii) Majority of existing works on efficient ViT and transformer techniques followed what has been done for Convolutional Neural Networks (CNNs) by using conventional weight pruning [10], [56], [57], [65], quantization [35], [40], [61], and compact architecture design [6], [8], [9], [16], [18], [31], [43], [49], [51],…”
MethodSwiftTron: An Efficient Hardware Accelerator for Quantized Transformers
Marchisio, A., Dura, D., Capra, M., Martina, M., Masera, G., & Shafique, M. (2023) · 2023 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10191521 · Cited by 39
Metadata
- Authors
- Prato, G., Charlaix, E., & Rezagholizadeh, M.
- Venue
- Findings of the Association for Computational Linguistics: EMNLP 2020
- Published
- 2020
- Pages
- 1-14
- OpenAlex
- W3012638462
- Cited by
- 59
- References
- 14
- FWCI
- 3.81
- Type
- conference paper
- Language
- en
- Open access
- gold
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: Fully Quantized Transformer for Machine Translation. https://app.cochat.ai/papers/10.18653/v1/2020.findings-emnlp.1
- The paper
- Prato, G., Charlaix, E., & Rezagholizadeh, M. (2020). Fully Quantized Transformer for Machine Translation. Findings of the Association for Computational Linguistics: EMNLP 2020. https://doi.org/10.18653/v1/2020.findings-emnlp.1
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.