English
Related papers

Related papers: Accelerating Transformer Inference for Translation…

200 papers

Independence assumptions during sequence generation can speed up inference, but parallel generation of highly inter-dependent tokens comes at a cost in quality. Instead of assuming independence between neighbouring tokens…

Computation and Language · Computer Science 2020-10-28 Biao Zhang , Ivan Titov , Rico Sennrich

Iterative processing is widely adopted nowadays in modern wireless receivers for advanced channel codes like turbo and LDPC codes. Extension of this principle with an additional iterative feedback loop to the demapping function has proven…

Information Theory · Computer Science 2015-06-04 Salim Haddad , Amer Baghdadi , Michel Jezequel

In this work, we empirically confirm that non-autoregressive translation with an iterative refinement mechanism (IR-NAT) suffers from poor acceleration robustness because it is more sensitive to decoding batch size and computing device…

Computation and Language · Computer Science 2022-10-20 Qiang Wang , Xinhui Hu , Ming Chen

Existing machine translation decoding algorithms generate translations in a strictly monotonic fashion and never revisit previous decisions. As a result, earlier mistakes cannot be corrected at a later stage. In this paper, we present a…

Computation and Language · Computer Science 2018-04-17 Roman Novak , Michael Auli , David Grangier

Multilingual translation suffers from computational redundancy, especially when translating into multiple languages simultaneously. In addition, translation quality can suffer for low-resource languages. To address this, we introduce…

Computation and Language · Computer Science 2026-03-18 Yiwen Guan , Jacob Whitehill

This paper addresses the problem of simultaneous machine translation (SiMT) by exploring two main concepts: (a) adaptive policies to learn a good trade-off between high translation quality and low latency; and (b) visual information to…

Computation and Language · Computer Science 2021-02-24 Julia Ive , Andy Mingren Li , Yishu Miao , Ozan Caglayan , Pranava Madhyastha , Lucia Specia

With the evergrowing sizes of pre-trained models (PTMs), it has been an emerging practice to only provide the inference APIs for users, namely model-as-a-service (MaaS) setting. To adapt PTMs with model parameters frozen, most current…

Computation and Language · Computer Science 2023-05-25 Ganqu Cui , Wentao Li , Ning Ding , Longtao Huang , Zhiyuan Liu , Maosong Sun

Maximum-a-posteriori (MAP) decoding is the most widely used decoding strategy for neural machine translation (NMT) models. The underlying assumption is that model probability correlates well with human judgment, with better translations…

Computation and Language · Computer Science 2024-07-12 Christian Tomani , David Vilar , Markus Freitag , Colin Cherry , Subhajit Naskar , Mara Finkelstein , Xavier Garcia , Daniel Cremers

A method is presented for accelerating inference in transformer language models by exploiting the low effective rank of the token activation manifold at each layer. The method decomposes each activation vector into a subspace component and…

Machine Learning · Computer Science 2026-05-06 Stephen J. Thomas

Simultaneous translation has many important application scenarios and attracts much attention from both academia and industry recently. Most existing frameworks, however, have difficulties in balancing between the translation quality and…

Computation and Language · Computer Science 2020-05-05 Renjie Zheng , Mingbo Ma , Baigong Zheng , Kaibo Liu , Liang Huang

Leveraging large language models for machine translation has demonstrated promising results. However, it does require the large language models to possess the capability of handling both the source and target languages in machine…

Computation and Language · Computer Science 2024-10-18 Chengpeng Fu , Xiaocheng Feng , Yichong Huang , Wenshuai Huo , Baohang Li , Hui Wang , Bin Qin , Ting Liu

This paper describes the Volctrans' submission to the WMT21 news translation shared task for German->English translation. We build a parallel (i.e., non-autoregressive) translation system using the Glancing Transformer, which enables fast…

Computation and Language · Computer Science 2021-09-27 Lihua Qian , Yi Zhou , Zaixiang Zheng , Yaoming Zhu , Zehui Lin , Jiangtao Feng , Shanbo Cheng , Lei Li , Mingxuan Wang , Hao Zhou

Speculative decoding accelerates Large Language Models (LLMs) inference by using a lightweight draft model to propose candidate tokens that are verified in parallel by the target model. However, existing draft model training objectives are…

Computation and Language · Computer Science 2026-05-12 Zihao An , Taichi Liu , Ziqiong Liu , Dong Li , Ruofeng Liu , Emad Barsoum

Large language models achieve strong machine translation quality but incur high inference cost and latency, posing challenges for simultaneous translation. Re-translation provides a practical solution for off-the-shelf LLMs by repeatedly…

Computation and Language · Computer Science 2026-01-06 Linxiao Zeng , Haoyun Deng , Kangyuan Shu , Shizhen Wang

Despite advances in multilingual neural machine translation (MNMT), we argue that there are still two major challenges in this area: data imbalance and representation degeneration. The data imbalance problem refers to the imbalance in the…

Computation and Language · Computer Science 2023-10-26 Wen Lai , Alexandra Chronopoulou , Alexander Fraser

This tutorial presents a comprehensive introduction to Speculative Decoding (SD), an advanced technique for LLM inference acceleration that has garnered significant research interest in recent years. SD is introduced as an innovative…

Computation and Language · Computer Science 2025-03-04 Heming Xia , Cunxiao Du , Yongqi Li , Qian Liu , Wenjie Li

In sequence-to-sequence Transformer ASR, autoregressive (AR) models achieve strong accuracy but suffer from slow decoding, while non-autoregressive (NAR) models enable parallel decoding at the cost of degraded performance. We propose a…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-26 Hao Yen , Pin-Jui Ku , Ante Jukić , Sabato Marco Siniscalchi

Parallel imaging has been an essential technique to accelerate MR imaging. Nevertheless, the acceleration rate is still limited due to the ill-condition and challenges associated with the undersampled reconstruction. In this paper, we…

Image and Video Processing · Electrical Eng. & Systems 2019-08-07 Yanxia Chen , Taohui Xiao , Cheng Li , Qiegen Liu , Shanshan Wang

Simultaneous translation (ST) starts translations synchronously while reading source sentences, and is used in many online scenarios. The previous wait-k policy is concise and achieved good results in ST. However, wait-k policy faces two…

Computation and Language · Computer Science 2020-12-24 Shaolei Zhang , Yang Feng , Liangyou Li

Improving Transformer efficiency has become increasingly attractive recently. A wide range of methods has been proposed, e.g., pruning, quantization, new architectures and etc. But these methods are either sophisticated in implementation or…

Machine Learning · Computer Science 2021-09-10 Ye Lin , Yanyang Li , Tong Xiao , Jingbo Zhu