10 citations · 37 across the 19 of their papers we have counts for
20 papers · 1 filter
A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM Integration into Upcycled MoE
Hao Zhou, Tianhao Li, Zhijun Wang +6
Expanding Large Language Models~(LLMs) to new languages is a costly endeavor, demanding extensive Continued Pre-Training~(CPT) and data-intensive alignment. While recent data-free…
EnAnchored-X2X: English-Anchored Optimization for Many-to-Many Translation
Sen Yang, Yu Bao, Yu Lu +3
Large language models (LLMs) have demonstrated strong machine translation capabilities for English-centric language pairs but underperform in direct non-English (x2x) translation.…
Trans-Zero: Self-Play Incentivizes Large Language Models for Multilingual Translation Without Parallel Data
Wei Zou, Sen Yang, Yu Bao +3
The rise of Large Language Models (LLMs) has reshaped machine translation (MT), but multilingual MT still relies heavily on parallel data for supervised fine-tuning (SFT), facing c…
Alleviating Distribution Shift in Synthetic Data for Machine Translation Quality Estimation
Xiang Geng, Zhejian Lai, Jiajun Chen +2
Quality Estimation (QE) models evaluate the quality of machine translations without reference translations, serving as the reward models for the translation task. Due to the data s…
MT-PATCHER: Selective and Extendable Knowledge Distillation from Large Language Models for Machine Translation
Jiahuan Li, Shanbo Cheng, Shujian Huang +1
Large Language Models (LLM) have demonstrated their strong ability in the field of machine translation (MT), yet they suffer from high computational cost and latency. Therefore, tr…
Selective Knowledge Distillation for Non-Autoregressive Neural Machine Translation
Min Liu, Yu Bao, Chengqi Zhao +1
Benefiting from the sequence-level knowledge distillation, the Non-Autoregressive Transformer (NAT) achieves great success in neural machine translation tasks. However, existing kn…
What Knowledge Is Needed? Towards Explainable Memory for kNN-MT Domain Adaptation
Wenhao Zhu, Shujian Huang, Yunzhe Lv +2
kNN-MT presents a new paradigm for domain adaptation by building an external datastore, which usually saves all target language token occurrences in the parallel corpus. As a resul…
Better Datastore, Better Translation: Generating Datastores from Pre-Trained Models for Nearest Neural Machine Translation
Jiahuan Li, Shanbo Cheng, Zewei Sun +2
Nearest Neighbor Machine Translation (kNNMT) is a simple and effective method of augmenting neural machine translation (NMT) with a token-level nearest neighbor retrieval mechanism…
Helping the Weak Makes You Strong: Simple Multi-Task Learning Improves Non-Autoregressive Translators
Xinyou Wang, Zaixiang Zheng, Shujian Huang
Recently, non-autoregressive (NAR) neural machine translation models have received increasing attention due to their efficient parallel decoding. However, the probabilistic framewo…
Zero-shot Domain Adaptation for Neural Machine Translation with Retrieved Phrase-level Prompts
Zewei Sun, Qingnan Jiang, Shujian Huang +3
Domain adaptation is an important challenge for neural machine translation. However, the traditional fine-tuning solution requires multiple extra training and yields a high cost. I…
Analyzing the Intensity of Complaints on Social Media
Ming Fang, Shi Zong, Jing Li +3
Complaining is a speech act that expresses a negative inconsistency between reality and human expectations. While prior studies mostly focus on identifying the existence or the typ…
-GLAT: Glancing at Latent Variables for Parallel Text Generation
Yu Bao, Hao Zhou, Shujian Huang +5
Recently, parallel text generation has received widespread attention due to its success in generation efficiency. Although many advanced techniques are proposed to improve its gene…
Non-Parametric Online Learning from Human Feedback for Neural Machine Translation
Dongqi Wang, Haoran Wei, Zhirui Zhang +3
We study the problem of online learning with human feedback in the human-in-the-loop machine translation, in which the human translators revise the machine-generated translations a…
Learning Kernel-Smoothed Machine Translation with Retrieved Examples
Qingnan Jiang, Mingxuan Wang, Jun Cao +3
How to effectively adapt neural machine translation (NMT) models according to emerging cases without retraining? Despite the great success of neural machine translation, updating t…
Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation
Xin Zheng, Zhirui Zhang, Shujian Huang +4
Recently, NN-MT has shown the promising capability of directly incorporating the pre-trained neural machine translation (NMT) model with domain-specific token-level -nearest-…
Energy-based Unknown Intent Detection with Data Manipulation
Yawen Ouyang, Jiasheng Ye, Yu Chen +3
Unknown intent detection aims to identify the out-of-distribution (OOD) utterance whose intent has never appeared in the training set. In this paper, we propose using energy scores…
Duplex Sequence-to-Sequence Learning for Reversible Machine Translation
Zaixiang Zheng, Hao Zhou, Shujian Huang +3
Sequence-to-sequence learning naturally has two directions. How to effectively utilize supervision signals from both directions? Existing approaches either require two separate mod…
FGraDA: A Dataset and Benchmark for Fine-Grained Domain Adaptation in Machine Translation
Wenhao Zhu, Shujian Huang, Tong Pu +6
Previous research for adapting a general neural machine translation (NMT) model into a specific domain usually neglects the diversity in translation within the same domain, which i…
Rethinking Document-level Neural Machine Translation
Zewei Sun, Mingxuan Wang, Hao Zhou +4
This paper does not aim at introducing a novel model for document-level neural machine translation. Instead, we head back to the original Transformer model and hope to answer the f…
Alleviating the Inequality of Attention Heads for Neural Machine Translation
Zewei Sun, Shujian Huang, Xin-Yu Dai +1
Recent studies show that the attention heads in Transformer are not equal. We relate this phenomenon to the imbalance training of multi-head attention and the model dependence on s…