Papers by Jingbo Zhu

Modality Adaption or Regularization? A Case Study on End-to-End Speech Translation (2023.acl-short)

Challenge:	Knowledge distillation is an effective method for model acceleration and compression.
Approach:	They propose to use parameters to distill knowledge from large neural networks to small ones . they propose to do this by using a parameter generator to transfer the knowledge to a small neural network .
Outcome:	The proposed method learns a small network 1.88 2.94x faster than the large network but with competitive BLEU points.

Copied to clipboard

Yuchen Han, Chen Xu, Tong Xiao, Jingbo Zhu

Bag of Tricks for Optimizing Transformer Efficiency (2021.findings-emnlp)

Challenge:	End-to-end speech translation models have limited training data and are often inefficient due to the inconsistency of length and representation between speech and text.
Approach:	They find that the "modality gap" between speech and text data is not a major problem in E2E ST . they decouple the encoder to speech encoder and text encoder, and they find that there is a 'capacity gap'
Outcome:	The proposed model achieves 29.0 for en-de and 40.3 for fr on the MuST-C dataset.

Copied to clipboard

Ye Lin, Yanyang Li, Tong Xiao, Jingbo Zhu

A Simple and Effective Approach to Robust Unsupervised Bilingual Dictionary Induction (2020.coling-main)

Challenge:	Improving Transformer efficiency has become increasingly attractive in recent years.
Approach:	They propose to combine pruning, quantization, new architectures and training strategies to improve Transformer efficiency.
Outcome:	The proposed methods improve the inference efficiency of a strong Transformer system by 3.80x on CPU and 2.52x on GPU.

Copied to clipboard

Yanyang Li, Yingfeng Luo, Ye Lin, Quan Du, Huizhen Wang, Shujian Huang, Tong Xiao, Jingbo Zhu

Responsible & Trustworthy NLP

Challenge:	Recent work has questioned the robustness of unsupervised bilingual dictionary induction methods on distant language pairs.
Approach:	They propose an iterative dimension reduction method to bridge this gap . they propose a method that initializes and self-learning and inducing a dictionary .
Outcome:	The proposed method achieves 13.64 55.53% accuracy between English and four distant languages.

Cross-layer Attention Sharing for Pre-trained Large Language Models (2026.tacl-1)

Copied to clipboard

Yongyu Mu, Yuzhang Wu, Yuchun Fan, Chenglong Wang, Hengyu Li, Jiali Zeng, Qiaozhi He, Murun Yang, Fandong Meng, Jie Zhou, Tong Xiao, Jingbo Zhu

Multi-Path Transformer is Better: A Case Study on Neural Machine Translation (2022.findings-emnlp)

Challenge:	Existing studies focus on compressing the Key-Value cache or grouping attention heads, while overlooking redundancy between layers.
Approach:	They propose a lightweight substitute for self-attention in well-trained LLMs that uses feed-forward networks to align attention heads between adjacent layers and low-rank matrices to approximate differences in layer-wise attention weights.
Outcome:	The proposed model reduces redundancy by sharing weights across layers while maintaining high response quality while reducing redundant calculations within 53% 84% of the total layers.

Copied to clipboard

Ye Lin, Shuhan Zhou, Yanyang Li, Anxiang Ma, Tong Xiao, Jingbo Zhu

RankPrompt: Step-by-Step Comparisons Make Language Models Better Reasoners (2024.lrec-main)

Challenge:	Extensive experiments on 12 WMT tasks show that shallower multi-path models can achieve similar or even better performance than the deeper model.
Approach:	They propose to use a parameter-efficient multi-path structure to fuse features extracted from different paths to achieve better performance.
Outcome:	The proposed model can achieve better performance with the same number of parameters than the deeper model.

Copied to clipboard

Chi Hu, Yuan Ge, Xiangnan Ma, Hang Cao, Qiang Li, Yonghua Yang, Tong Xiao, Jingbo Zhu

Dialogue Systems & Conversational Agents

Challenge:	Existing solutions to reasoning tasks require extensive human annotations or fail in scenarios with inconsistent responses.
Approach:	They propose a new method that enables LLMs to self-rank their responses without additional resources.
Outcome:	The proposed method improves reasoning performance of ChatGPT and GPT-4 with 13% improvement over existing methods.

Bridging the Granularity Gap for Acoustic Modeling (2023.findings-acl)

Copied to clipboard

Chen Xu, Yuhao Zhang, Chengbo Jiao, Xiaoqian Liu, Chi Hu, Xin Zeng, Tong Xiao, Anxiang Ma, Huizhen Wang, Jingbo Zhu

Multimodality

Challenge:	Despite the success of speech recognition, how to encode the speech features effectively remains an open problem.
Approach:	They propose a Progressive Down-Sampling technique which compresses acoustic features into coarser-grained units containing more complete semantic information, like text-level representation.
Outcome:	The proposed method yields comparable or better results on the speech recognition task and inference speedups ranging from 1.20x to 1.47x.

Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translation (2020.acl-main)

Copied to clipboard

Bei Li, Hui Liu, Ziyang Wang, Yufan Jiang, Tong Xiao, Jingbo Zhu, Tongran Liu, Changliang Li

MobileNMT: Enabling Translation in 15MB and 30ms (2023.acl-industry)

Challenge:	In encoder-decoder neural models, multiple encoders are used to represent contextual information in addition to the individual sentence.
Approach:	They propose to use multiple context encoders to encode the individual sentences in document-level neural machine translation (NMT) They propose a noisy dropout setup and a single-encoder approach to encode context sentences.
Outcome:	The proposed approach encodes the context and the current sentence without contexts.

Copied to clipboard

Ye Lin, Xiaohui Wang, Zhexi Zhang, Mingxuan Wang, Tong Xiao, Jingbo Zhu

Dynamic Curriculum Learning for Low-Resource Neural Machine Translation (2020.coling-main)

Challenge:	Existing work on NMT models is limited in storage, memory, computation and power consumption.
Approach:	They propose a mobile machine translation system that can translate in 15MB and 30ms on devices.
Outcome:	The proposed system can translate in 15MB and 30ms on mobile devices.

Copied to clipboard

Chen Xu, Bojie Hu, Yufan Jiang, Kai Feng, Zeyang Wang, Shen Huang, Qi Ju, Tong Xiao, Jingbo Zhu

Text Generation

Challenge:	Recent work on neural machine translation (NMT) has demonstrated impressive performance improvements and became the de-facto standard.
Approach:	They propose a dynamic curriculum learning method to reorder training samples in training using a Transformer-based system.
Outcome:	The proposed method outperforms baselines on three low-resource machine translation benchmarks and different sized data of WMT’16 En-De.

RankNAS: Efficient Neural Architecture Search by Pairwise Ranking (2021.emnlp-main)

Copied to clipboard

Chi Hu, Chenglong Wang, Xiangnan Ma, Xia Meng, Yinqiao Li, Tong Xiao, Jingbo Zhu, Changliang Li

Green & Sustainable NLP

Challenge:	Existing methods require training millions of architectures to estimate the accuracy of the search results.
Approach:	They propose a performance ranking method (RankNAS) that uses pairwise ranking and search space pruning to enlarge the search space.
Outcome:	The proposed method significantly accelerates NAS through pairwise ranking and search space pruning.

SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment (2025.coling-main)

Copied to clipboard

Yuchun Fan, Yongyu Mu, YiLin Wang, Lei Huang, Junhao Ruan, Bei Li, Tong Xiao, Shujian Huang, Xiaocheng Feng, Jingbo Zhu

Responsible & Trustworthy NLP

Challenge:	Large language models (LLMs) have demonstrated significant improvements in reasoning abilities, but these improvements are primarily focused on English, leading to inferior performance in non-English scenarios.
Approach:	They propose a multilingual reasoning alignment approach that fine-tunes the layers responsible for multilingual comprehension in one stage.
Outcome:	The proposed method fine-tunes 6 of the 9 layers responsible for multilingual comprehension, while reducing training time by 4.1-11.9 compared to the two-stage method.

CTC-based Non-autoregressive Speech Translation (2023.acl-long)

Copied to clipboard

Chen Xu, Xiaoqian Liu, Xiaowen Liu, Qingxuan Sun, Yuhao Zhang, Murun Yang, Qianqian Dong, Tom Ko, Mingxuan Wang, Tong Xiao, Anxiang Ma, Jingbo Zhu

Machine Translation

Challenge:	End-to-end speech translation (E2E ST) and non-autoregressive (NAR) generation are promising in language and speech processing for their advantages of less error propagation and low latency.
Approach:	They develop a model that uses connectionist temporal classification to predict the source and target texts.
Outcome:	The proposed model achieves an average BLEU score of 29.5 with a speed-up of 5.67.

TranSFormer: Slow-Fast Transformer for Machine Translation (2023.findings-acl)

Copied to clipboard

Bei Li, Yi Jing, Xu Tan, Zhen Xing, Tong Xiao, Jingbo Zhu

Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders (2021.acl-long)

Challenge:	Prior work has focused on treating subwords as basic units in developing such systems.
Approach:	They propose a slow-fast two-stream learning model that uses a “slow” branch to deal with subword sequences and a "fast" branch to cope with longer character sequences.
Outcome:	The proposed model shows consistent BLEU improvements (larger than 1 BLUE point) on several machine translation benchmarks.

Copied to clipboard

Chen Xu, Bojie Hu, Yanyang Li, Yuhao Zhang, Shen Huang, Qi Ju, Tong Xiao, Jingbo Zhu

Text Generation

Challenge:	End-to-end Speech Translation (E2E ST) encoders lack global context representation, whereas MT encoder lacks it.
Approach:	They propose a Stacked Acoustic-and-Textual Encoding method for speech translation . they propose an adaptor module to alleviate representation inconsistency .
Outcome:	The proposed method achieves state-of-the-art BLEU scores of 18.3 and 25.2 on two ST tasks.

Improving Autoregressive Grammatical Error Correction with Non-autoregressive Models (2023.findings-acl)

Copied to clipboard

Hang Cao, Zhiquan Cao, Chi Hu, Baoyu Hou, Tong Xiao, Jingbo Zhu

Syntactic Text Processing

Challenge:	Autoregressive models assign low probabilities to tokens that need corrections . grammatical error correction (GEC) is widely applied to natural language processing tasks .
Approach:	They propose to use a non-autoregressive model as an auxiliary model to train GEC models to correct grammatical errors in sentences.
Outcome:	The proposed method outperforms baselines on English and Chinese GEC tasks significantly.

Improved Knowledge Distillation for Pre-trained Language Models via Knowledge Selection (2022.findings-emnlp)

Copied to clipboard

Chenglong Wang, Yi Lu, Yongyu Mu, Yimin Hu, Tong Xiao, Jingbo Zhu

Multi-layer Representation Fusion for Neural Machine Translation (C18-1)

Challenge:	Existing studies on knowledge distillation have shown that not all knowledge is necessary for learning a good student model.
Approach:	They propose an actor-critic approach to selecting appropriate knowledge to transfer during the process of knowledge distillation.
Outcome:	The proposed method outperforms several strong knowledge distillation baselines significantly on the GLUE datasets.

Copied to clipboard

Qiang Wang, Fuxue Li, Tong Xiao, Yanyang Li, Yinqiao Li, Jingbo Zhu

Learning Architectures from an Extended Search Space for Language Modeling (2020.acl-main)

Challenge:	Neural machine translation systems require a number of stacked layers for deep models, but the prediction depends on the sentence representation of the top-most layer with no access to low-level representations.
Approach:	They propose a multi-layer representation fusion approach to fusing stacked layers to learn a better representation from the stack.
Outcome:	The proposed approach yields 0.92 and 0.56 BLEU points over the strong Transformer baseline on IWSLT German-English and NIST Chinese-English MT tasks respectively.

Copied to clipboard

Yinqiao Li, Chi Hu, Yuhao Zhang, Nuo Xu, Yufan Jiang, Tong Xiao, Jingbo Zhu, Tongran Liu, Changliang Li

Training Flexible Depth Model by Multi-Task Learning for Neural Machine Translation (2020.findings-emnlp)

Challenge:	Neural architecture search (NAS) has advanced in recent years but most NAS systems restrict search to learning architectures of a recurrent or convolutional cell.
Approach:	They propose a general approach to learn both intra-cell and inter-cell architectures . they implement their approach in a differentiable architecture search system .
Outcome:	The proposed approach outperforms the baseline on PTB and WikiText data and shows good transferability to other systems.

Copied to clipboard

Qiang Wang, Tong Xiao, Jingbo Zhu

Augmenting Large Language Model Translators via Translation Memories (2023.findings-acl)

Challenge:	Experimental results show that multitask learning can support decoding in 24 depth configurations and is superior to individual training.
Approach:	They propose to use multi-task learning to train a flexible depth model that can adapt to different depth configurations during inference.
Outcome:	The proposed model can support decoding in 24 depth configurations and is superior to the individual training and another flexible depth model training method——LayerDrop.

Copied to clipboard

Yongyu Mu, Abudurexiti Reheman, Zhiquan Cao, Yuchun Fan, Bei Li, Yinqiao Li, Tong Xiao, Chunliang Zhang, Jingbo Zhu

Layer-Wise Multi-View Learning for Neural Machine Translation (2020.coling-main)

Challenge:	Using translation memories (TMs) as prompts is a promising approach to in-context learning of machine translation models.
Approach:	They propose to use translation memories (TMs) as prompts to prompt large language models (LLMs) they find that the ability of LLMs to "understand" prompts is helpful .
Outcome:	The results are comparable to state-of-the-art NMT systems with bilingual data and are tuned on downstream tasks.

Copied to clipboard

Qiang Wang, Changliang Li, Yue Zhang, Tong Xiao, Jingbo Zhu

Machine Translation

Challenge:	Existing approaches to neural machine translation are limited to the topmost encoder layer’s context representation and cannot perceive the lower encoder layers.
Approach:	They propose a layer-wise multi-view learning approach to solve this problem by incorporating an auxiliary view into the model.
Outcome:	The proposed model can achieve stable results over multiple strong baselines and is agnostic to network architectures.

A Simple and Effective Approach to Coverage-Aware Neural Machine Translation (P18-2)

Copied to clipboard

Yanyang Li, Tong Xiao, Yinqiao Li, Qiang Wang, Changming Xu, Jingbo Zhu

Shallow-to-Deep Training for Neural Machine Translation (2020.emnlp-main)

Challenge:	Neural Machine Translation (NMT) models are used to solve translation problems using long-term models.
Approach:	They propose a method to seek a better balance between model confidence and length preference for Neural Machine Translation.
Outcome:	The proposed model improves on Chinese-English and English-German translation tasks.

Copied to clipboard

Bei Li, Ziyang Wang, Hui Liu, Yufan Jiang, Quan Du, Tong Xiao, Huizhen Wang, Jingbo Zhu

Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection (2026.acl-long)

Challenge:	Experimental results show that deep training is 1:4 faster than training from scratch.
Approach:	They propose a shallow-to-deep training method that learns deep models by stacking shallow models.
Outcome:	The proposed method is 1:4 faster than training from scratch and achieves BLEU scores of 30:33 and 43:29 on two translation tasks.

Copied to clipboard

Yuwei Zhang, Wenhao Yu, Shangbin Feng, Yifan Zhu, Letian Peng, Jayanth Srinivasa, Gaowen Liu, Jingbo Shang

Improved Differentiable Architecture Search for Language Modeling and Named Entity Recognition (D19-1)

Challenge:	Existing knowledge injection benchmarks for large language models lack standardized testing grounds.
Approach:	They propose a knowledge injection benchmark that leverages recently-added and expert-curated facts from Wikipedia’s “Did You Know...” entries.
Outcome:	The proposed framework improves reliability accuracy by 29.1%.

Copied to clipboard

Yufan Jiang, Chi Hu, Tong Xiao, Chunliang Zhang, Jingbo Zhu

Learning Deep Transformer Models for Machine Translation (P19-1)

Challenge:	Neural architecture search (NAS) is a popular approach for finding new models and freeing researchers from the hard work of designing network architectures.
Approach:	They propose differentiable neural architecture search methods for natural language processing . they remove the softmax-local constraint and apply it to named entity recognition .
Outcome:	The proposed method outperforms strong baselines on the language modeling task.

Copied to clipboard

Qiang Wang, Bei Li, Tong Xiao, Jingbo Zhu, Changliang Li, Derek F. Wong, Lidia S. Chao