activity
20162024
most citedNeural Machine Translation with Reconstruction

60 citations · 126 across the 14 of their papers we have counts for

collaborators

14 papers

cs.LG202422 cited

VN Network: Embedding Newly Emerging Entities with Virtual Neighbors

Yongquan He, Zihan Wang, Peng Zhang +2

Embedding entities and relations into continuous vector spaces has attracted a surge of interest in recent years. Most embedding methods assume that all test entities are available…

cs.CL20241 cited

Unsupervised Sign Language Translation and Generation

Zhengsheng Guo, Zhiwei He, Wenxiang Jiao +6

Motivated by the success of unsupervised neural machine translation (UNMT), we introduce an unsupervised sign language translation and generation network (USLNet), which learns fro…

cs.CL2024

Revisiting the Markov Property for Machine Translation

Cunxiao Du, Hao Zhou, Zhaopeng Tu +1

In this paper, we re-examine the Markov property in the context of neural machine translation. We design a Markov Autoregressive Transformer~(MAT) and undertake a comprehensive ass…

cs.CL2024

GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding

Cunxiao Du, Jing Jiang, Xu Yuanchen +8

Speculative decoding is a relatively new decoding framework that leverages small and efficient draft models to reduce the latency of LLMs. In this study, we introduce GliDe and CaP…

cs.CL2024

Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model

Zhiwei He, Xing Wang, Wenxiang Jiao +4

Insufficient modeling of human preferences within the reward model is a major obstacle for leveraging human feedback to improve translation quality. Fortunately, quality estimation…

cs.CL20231 cited

Findings of the WMT 2023 Shared Task on Discourse-Level Literary Translation: A Fresh Orb in the Cosmos of LLMs

Longyue Wang, Zhaopeng Tu, Yan Gu +14

Translating literary works has perennially stood as an elusive dream in machine translation (MT), a journey steeped in intricate challenges. To foster progress in this domain, we h…