Zobrazeno 1 - 10
of 315
pro vyhledávání: '"Ding,Chenchen"'
Existing multilingual neural machine translation (MNMT) approaches mainly focus on improving models with the encoder-decoder architecture to translate multiple languages. However, decoder-only architecture has been explored less in MNMT due to its un
Externí odkaz:
http://arxiv.org/abs/2412.02101
Understanding representation transfer in multilingual neural machine translation can reveal the representational issue causing the zero-shot translation deficiency. In this work, we introduce the identity pair, a sentence translated into itself, to a
Externí odkaz:
http://arxiv.org/abs/2406.08092
Lightweight design of Convolutional Neural Networks (CNNs) requires co-design efforts in the model architectures and compression techniques. As a novel design paradigm that separates training and inference, a structural re-parameterized (SR) network
Externí odkaz:
http://arxiv.org/abs/2402.07200
Autor:
Ding, Chenchen
$f \propto r^{-\alpha} \cdot (r+\gamma)^{-\beta}$ has been empirically shown more precise than a na\"ive power law $f\propto r^{-\alpha}$ to model the rank-frequency ($r$-$f$) relation of words in natural languages. This work shows that the only cruc
Externí odkaz:
http://arxiv.org/abs/2402.00271
Autor:
Cao, Yuqi a, Liu, Yingpei b, Ding, Chenchen a, Ma, Tingting a, Ye, Huimin a, Zhong, Weiwei a, He, Wei a, ⁎
Publikováno v:
In Diamond & Related Materials January 2025 151
Autor:
Ding, Chenchen
Let $f (\cdot)$ be the absolute frequency of words and $r$ be the rank of words in decreasing order of frequency, then the following function can fit the rank-frequency relation \[ f (r;s,t) = \left(\frac{r_{\tt max}}{r}\right)^{1-s} \left(\frac{r_{\
Externí odkaz:
http://arxiv.org/abs/2205.00638
Publikováno v:
In International Immunopharmacology 25 December 2024 143 Part 2
Autor:
Ma, Tingting a, Guo, Mingzhi a, Cao, Yuqi a, Zhong, Weiwei b, Ding, Chenchen b, Ye, Huimin a, Chen, Luyu a, Xu, Hong c, d, Fang, Zheng a, d, He, Wei a, d, ⁎
Publikováno v:
In Journal of Environmental Chemical Engineering December 2024 12(6)
Autor:
Ding, Chenchen a, Zhong, Weiwei a, Cao, Yuqi a, Ma, Tingting a, Ye, Huimin a, Fang, Zheng a, Feng, Yirong a, Zhao, Shuangfei a, Yang, Jiming a, Li, Yuguang b, Shen, Lei b, He, Wei a, ⁎
Publikováno v:
In Chemical Engineering Science 5 February 2025 302 Part A
Autor:
Liu, Qianying, Gong, Zhuo, Yang, Zhengdong, Yang, Yuhang, Li, Sheng, Ding, Chenchen, Minematsu, Nobuaki, Huang, Hao, Cheng, Fei, Chu, Chenhui, Kurohashi, Sadao
Low-resource speech recognition has been long-suffering from insufficient training data. In this paper, we propose an approach that leverages neighboring languages to improve low-resource scenario performance, founded on the hypothesis that similar l
Externí odkaz:
http://arxiv.org/abs/2204.03855