Zobrazeno 1 - 10
of 572
pro vyhledávání: '"Geng, Xiang"'
Autor:
Geng, Xiang, Zhu, Ming, Li, Jiahuan, Lai, Zhejian, Zou, Wei, She, Shuaijie, Guo, Jiaxin, Zhao, Xiaofeng, Li, Yinglu, Li, Yuang, Su, Chang, Zhao, Yanqing, Lyu, Xinglin, Zhang, Min, Chen, Jiajun, Yang, Hao, Huang, Shujian
The scarcity of non-English data limits the development of non-English large language models (LLMs). Transforming English-centric LLMs to non-English has been identified as an effective and resource-efficient method. Previous works start from base LL
Externí odkaz:
http://arxiv.org/abs/2405.13923
Autor:
Zhao, Haofei, Liu, Yilun, Tao, Shimin, Meng, Weibin, Chen, Yimeng, Geng, Xiang, Su, Chang, Zhang, Min, Yang, Hao
Publikováno v:
2024 International Joint Conference on Neural Networks (IJCNN)
Machine Translation Quality Estimation (MTQE) is the task of estimating the quality of machine-translated text in real time without the need for reference translations, which is of great importance for the development of MT. After two decades of evol
Externí odkaz:
http://arxiv.org/abs/2403.14118
Though reasoning abilities are considered language-agnostic, existing LLMs exhibit inconsistent reasoning abilities across different languages, e.g., reasoning in the dominant language like English is superior to other languages due to the imbalance
Externí odkaz:
http://arxiv.org/abs/2401.06838
This study investigates how Large Language Models (LLMs) leverage source and reference data in machine translation evaluation task, aiming to better understand the mechanisms behind their remarkable performance in this task. We design the controlled
Externí odkaz:
http://arxiv.org/abs/2401.06568
Autor:
Geng, Xiang, Li, Zhaojin, Zhang, Chengfeng, Wang, Yanjie, Shen, Haoning, Huang, Zhiheng, Hou, Yawen, Chen, Zheng
Computation of sample size is important when designing clinical trials. The presence of competing risks makes the design of clinical trials with time-to-event endpoints cumbersome. A model based on the subdistribution hazard ratio (SHR) is commonly u
Externí odkaz:
http://arxiv.org/abs/2311.12293
We introduce the submissions of the NJUNLP team to the WMT 2023 Quality Estimation (QE) shared task. Our team submitted predictions for the English-German language pair on all two sub-tasks: (i) sentence- and word-level quality prediction; and (ii) f
Externí odkaz:
http://arxiv.org/abs/2309.13230
Abstractive summarization is the process of generating a summary given a document as input. Although significant progress has been made, the factual inconsistency between the document and the generated summary still limits its practical applications.
Externí odkaz:
http://arxiv.org/abs/2212.01611
Autor:
Geng, Xiang, Li, Yuxi, Hao, Ruochen, Xu, Chunyan, Li, Zhun, Yang, Yajun, Liu, Xiwang, Li, Jianyong, Pu, Wanxia
Publikováno v:
In International Journal of Antimicrobial Agents November 2024 64(5)
Autor:
Geng, Xiang, Qi, Qiang, Wang, Wu, Guo, Tom, Cai, Yubo, Gu, Shouxi, Zhu, Qingjun, Zhou, Hai-Shan, Liu, Songlin, Luo, Guang-Nan
Publikováno v:
In Nuclear Materials and Energy September 2024 40
Publikováno v:
In Nuclear Materials and Energy September 2024 40