97 citations · 129 across the 21 of their papers we have counts for
21 papers
Soft Alignment of Modality Space for End-to-end Speech Translation
Yuhao Zhang, Kaiqi Kou, Bei Li +4
End-to-end Speech Translation (ST) aims to convert speech into target text within a unified model. The inherent differences between speech and text modalities often impede effectiv…
Rethinking and Improving Multi-task Learning for End-to-end Speech Translation
Yuhao Zhang, Chen Xu, Bei Li +4
Significant improvements in end-to-end speech translation (ST) have been achieved through the application of multi-task learning. However, the extent to which auxiliary tasks are h…
Incorporating Probing Signals into Multimodal Machine Translation via Visual Question-Answering Pairs
Yuxin Zuo, Bei Li, Chuanhao Lv +3
This paper presents an in-depth study of multimodal machine translation (MMT), examining the prevailing understanding that MMT systems exhibit decreased sensitivity to visual infor…
ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation
Chenglong Wang, Hang Zhou, Yimin Hu +5
Applying Reinforcement Learning (RL) to sequence generation models enables the direct optimization of long-term rewards (\textit{e.g.,} BLEU and human feedback), but typically requ…
ManagerTower: Aggregating the Insights of Uni-Modal Experts for Vision-Language Representation Learning
Xiao Xu, Bei Li, Chenfei Wu +6
Two-Tower Vision-Language (VL) models have shown promising improvements on various downstream VL tasks. Although the most advanced work improves performance by building bridges bet…
Deliberate then Generate: Enhanced Prompting Framework for Text Generation
Bei Li, Rui Wang, Junliang Guo +7
Large language models (LLMs) have shown remarkable success across a wide range of natural language generation tasks, where proper prompt designs make great impacts. While existing…
Augmenting Large Language Model Translators via Translation Memories
Yongyu Mu, Abudurexiti Reheman, Zhiquan Cao +6
Using translation memories (TMs) as prompts is a promising approach to in-context learning of machine translation models. In this work, we take a step towards prompting large langu…
TranSFormer: Slow-Fast Transformer for Machine Translation
Bei Li, Yi Jing, Xu Tan +3
Learning multiscale Transformer models has been evidenced as a viable approach to augmenting machine translation systems. Prior research has primarily focused on treating subwords…
EIT: Enhanced Interactive Transformer
Tong Zheng, Bei Li, Huiwen Bao +2
Two principles: the complementary principle and the consensus principle are widely acknowledged in the literature of multi-view learning. However, the current design of multi-head…
Learning Multiscale Transformer Models for Sequence Generation
Bei Li, Tong Zheng, Yi Jing +3
Multiscale feature hierarchies have been witnessed the success in the computer vision area. This further motivates researchers to design multiscale Transformer for natural language…
ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation
Bei Li, Quan Du, Tao Zhou +7
Residual networks are an Euler discretization of solutions to Ordinary Differential Equations (ODE). This paper explores a deeper relationship between Transformer and numerical ODE…
On Vision Features in Multimodal Machine Translation
Bei Li, Chuanhao Lv, Zefan Zhou +4
Previous work on multimodal machine translation (MMT) has focused on the way of incorporating vision features into translation but little attention is on the quality of vision mode…
The NiuTrans Machine Translation Systems for WMT21
Shuhan Zhou, Tao Zhou, Binghao Wei +15
This paper describes NiuTrans neural machine translation systems of the WMT 2021 news translation tasks. We made submissions to 9 language directions, including English$\leftrighta…
The NiuTrans System for WNGT 2020 Efficiency Task
Chi Hu, Bei Li, Ye Lin +5
This paper describes the submissions of the NiuTrans Team to the WNGT 2020 Efficiency Shared Task. We focus on the efficient implementation of deep Transformer models \cite{wang-et…
The NiuTrans System for the WMT21 Efficiency Task
Chenglong Wang, Chi Hu, Yongyu Mu +8
This paper describes the NiuTrans system for the WMT21 translation efficiency task (http://statmt.org/wmt21/efficiency-task.html). Following last year's work, we explore various te…
ODE Transformer: An Ordinary Differential Equation-Inspired Model for Neural Machine Translation
Bei Li, Quan Du, Tao Zhou +4
It has been found that residual networks are an Euler discretization of solutions to Ordinary Differential Equations (ODEs). In this paper, we explore a deeper relationship between…
Learning Light-Weight Translation Models from Deep Transformer
Bei Li, Ziyang Wang, Hui Liu +4
Recently, deep models have shown tremendous improvements in neural machine translation (NMT). However, systems of this kind are computationally expensive and memory intensive. In t…
Shallow-to-Deep Training for Neural Machine Translation
Bei Li, Ziyang Wang, Hui Liu +5
Deep encoders have been proven to be effective in improving neural machine translation (NMT) systems, but training an extremely deep encoder is time consuming. Moreover, why deep m…
Weight Distillation: Transferring the Knowledge in Neural Network Parameters
Ye Lin, Yanyang Li, Ziyang Wang +4
Knowledge distillation has been proven to be effective in model acceleration and compression. It allows a small network to learn to generalize in the same way as a large network. R…
Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translation
Bei Li, Hui Liu, Ziyang Wang +5
In encoder-decoder neural models, multiple encoders are in general used to represent the contextual information in addition to the individual sentence. In this paper, we investigat…
Learning Deep Transformer Models for Machine Translation
Qiang Wang, Bei Li, Tong Xiao +4
Transformer is the state-of-the-art model in recent machine translation evaluations. Two strands of research are promising to improve models of this kind: the first uses wide netwo…