Zobrazeno 1 - 10
of 266
pro vyhledávání: '"Sun, Zewei"'
Autor:
Zhang, Liding, Cai, Kuanqi, Sun, Zewei, Bing, Zhenshan, Wang, Chaoqun, Figueredo, Luis, Haddadin, Sami, Knoll, Alois
Recent advancements in robotics have transformed industries such as manufacturing, logistics, surgery, and planetary exploration. A key challenge is developing efficient motion planning algorithms that allow robots to navigate complex environments wh
Externí odkaz:
http://arxiv.org/abs/2410.19414
Document-level Neural Machine Translation (DocNMT) has been proven crucial for handling discourse phenomena by introducing document-level context information. One of the most important directions is to input the whole document directly to the standar
Externí odkaz:
http://arxiv.org/abs/2309.14174
Autor:
Kang, Liyan, Huang, Luyang, Peng, Ningxin, Zhu, Peihao, Sun, Zewei, Cheng, Shanbo, Wang, Mingxuan, Huang, Degen, Su, Jinsong
We present a large-scale video subtitle translation dataset, BigVideo, to facilitate the study of multi-modality machine translation. Compared with the widely used How2 and VaTeX datasets, BigVideo is more than 10 times larger, consisting of 4.5 mill
Externí odkaz:
http://arxiv.org/abs/2305.18326
Multimodal machine translation (MMT) aims to improve translation quality by incorporating information from other modalities, such as vision. Previous MMT systems mainly focus on better access and use of visual information and tend to validate their m
Externí odkaz:
http://arxiv.org/abs/2212.10313
Controlling styles in neural machine translation (NMT) has attracted wide attention, as it is crucial for enhancing user experience. Earlier studies on this topic typically concentrate on regulating the level of formality and achieve some progress in
Externí odkaz:
http://arxiv.org/abs/2212.08909
Nearest Neighbor Machine Translation (kNNMT) is a simple and effective method of augmenting neural machine translation (NMT) with a token-level nearest neighbor retrieval mechanism. The effectiveness of kNNMT directly depends on the quality of retrie
Externí odkaz:
http://arxiv.org/abs/2212.08822
Domain adaptation is an important challenge for neural machine translation. However, the traditional fine-tuning solution requires multiple extra training and yields a high cost. In this paper, we propose a non-tuning paradigm, resolving domain adapt
Externí odkaz:
http://arxiv.org/abs/2209.11409
Autor:
Lyu, Zhendong, Chen, Xiaohan, Wei, Ting, Wang, Difeng, Zhao, Puhui, Sanganyado, Edmond, Chi, Duowen, Sun, Zewei, Wang, Tieyu, Li, Ping, Liu, Wenhua, Bi, Ran
Publikováno v:
In Marine Pollution Bulletin October 2024 207
Autor:
Jiang, Tianzong, Gai, Shili, Yin, Yanqi, Sun, Zewei, Zhou, Bingchen, Zhao, Yubo, Ding, He, Ahmad Ansari, Anees, Yang, Piaoping
Publikováno v:
In Chemical Engineering Journal 1 September 2024 495
Autor:
Li, Yunfei *, Zhou, Xinying *, Du, Yusong *, An, Mingyuan *, Wan, Shasha *, Sun, Zewei *, Zhong, Qingzhen *
Publikováno v:
In Poultry Science December 2024 103(12)