activity
20162024
most citedSearch for new high-mass phenomena in the dilepton final state using 36 fb of proton-proton collision data at = 13 TeV with the ATLAS detector

297 citations · 3.3k across the 61 of their papers we have counts for

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2024

Concise and Precise Context Compression for Tool-Using Language Models

Yang Xu, Yunlong Feng, Honglin Mu +9

Through reading the documentation in the context, tool-using language models can dynamically extend their capability using external tools. The cost is that we have to input lengthy…

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…

cs.CL2023

Non-autoregressive Streaming Transformer for Simultaneous Translation

Zhengrui Ma, Shaolei Zhang, Shoutao Guo +3

Simultaneous machine translation (SiMT) models are trained to strike a balance between latency and translation quality. However, training these models to achieve high quality while…

cs.CL2023

RenewNAT: Renewing Potential Translation for Non-Autoregressive Transformer

Pei Guo, Yisheng Xiao, Juntao Li +1

Non-autoregressive neural machine translation (NAT) models are proposed to accelerate the inference process while maintaining relatively high performance. However, existing NAT mod…

cs.CL20236 cited

A Multi-task Multi-stage Transitional Training Framework for Neural Chat Translation

Chulun Zhou, Yunlong Liang, Fandong Meng +5

Neural chat translation (NCT) aims to translate a cross-lingual chat between speakers of different languages. Existing context-aware NMT models cannot achieve satisfactory performa…

cs.CL20215 cited

Diformer: Directional Transformer for Neural Machine Translation

Minghan Wang, Jiaxin Guo, Yuxia Wang +8

Autoregressive (AR) and Non-autoregressive (NAR) models have their own superiority on the performance and latency, combining them into one model may take advantage of both. Current…