activity
20212024
most citedSelf-Distillation Mixup Training for Non-autoregressive Neural Machine Translation

8 citations · 17 across the 7 of their papers we have counts for

collaborators

10 papers

cs.CL2025

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation

Zhanglin Wu, Daimeng Wei, Xiaoyu Chen +7

Large language model (LLM) shows promising performances in a variety of downstream tasks, such as machine translation (MT). However, using LLMs for translation suffers from high co…

cs.CL2024

M-Ped: Multi-Prompt Ensemble Decoding for Large Language Models

Jiaxin Guo, Daimeng Wei, Yuanchang Luo +8

With the widespread application of Large Language Models (LLMs) in the field of Natural Language Processing (NLP), enhancing their performance has become a research hotspot. This p…

cs.CL2024

An End-to-End Speech Summarization Using Large Language Model

Hengchao Shang, Zongyao Li, Jiaxin Guo +5

Abstractive Speech Summarization (SSum) aims to generate human-like text summaries from spoken content. It encounters difficulties in handling long speech input and capturing the i…

cs.CL2024

A Novel Paradigm Boosting Translation Capabilities of Large Language Models

Jiaxin Guo, Hao Yang, Zongyao Li +3

This paper presents a study on strategies to enhance the translation capabilities of large language models (LLMs) in the context of machine translation (MT) tasks. The paper propos…

cs.CL20242 cited

R-BI: Regularized Batched Inputs enhance Incremental Decoding Framework for Low-Latency Simultaneous Speech Translation

Jiaxin Guo, Zhanglin Wu, Zongyao Li +6

Incremental Decoding is an effective framework that enables the use of an offline model in a simultaneous setting without modifying the original model, making it suitable for Low-L…

cs.CL20242 cited

UCorrect: An Unsupervised Framework for Automatic Speech Recognition Error Correction

Jiaxin Guo, Minghan Wang, Xiaosong Qiao +9

Error correction techniques have been used to refine the output sentences from automatic speech recognition (ASR) models and achieve a lower word error rate (WER). Previous works u…