47 citations · 51 across the 4 of their papers we have counts for
5 papers · 1 filter
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…
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…
ngram-OAXE: Phrase-Based Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation
Cunxiao Du, Zhaopeng Tu, Longyue Wang +1
Recently, a new training oaxe loss has proven effective to ameliorate the effect of multimodality for non-autoregressive translation (NAT), which removes the penalty of word order…
Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation
Cunxiao Du, Zhaopeng Tu, Jing Jiang
We propose a new training objective named order-agnostic cross entropy (OaXE) for fully non-autoregressive translation (NAT) models. OaXE improves the standard cross-entropy loss t…
Explicit Interaction Model towards Text Classification
Cunxiao Du, Zhaozheng Chin, Fuli Feng +3
Text classification is one of the fundamental tasks in natural language processing. Recently, deep neural networks have achieved promising performance in the text classification ta…