|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Recent advances and challenges in task-oriented dialog systems显示文摘Due to the significance and value in human-computer interaction and natural language processing,task-oriented dialog systems are attracting more and more attention in both academic and industrial communities.In this paper,we survey recent advances and challenges in task-oriented dialog systems.We also discuss three critical topics for task-oriented dialog systems:(1)improving data efficiency to facilitate dialog modeling in low-resource settings,(2)modeling multi-turn dynamics for dialog policy learning to achieve better task-completion performance,and(3)integrating domain ontology knowledge into the dialog model.Besides,we review the recent progresses in dialog evaluation and some widely-used corpora.We believe that this survey,though incomplete,can shed a light on future research in task-oriented dialog systems. | ZHANG Zheng TAKANOBU Ryuichi ZHU Qi HUANG MinLie ZHU XiaoYan | 2020 | Science China(Technological Sciences)2020，63，10： | 8 |
| 2 | Low concentrations of the recombinant toxin protein rLj-RGD3 suppress TNF-a-induced human renal carcinoma cell invasion显示文摘肾的房间癌(RCC ) 的一个特点侵略由 gelatinase 酶的本地生产是细胞外的矩阵(ECM ) 的降级。矩阵 metalloproteinase-9 (MMP-9 ) 导致了癌症房间侵略是在癌症的枢轴的步之一转移。它被报导了那个肿瘤坏死因素 --(TNF-) , MMP-9 的一个管理者,能在人的肾的癌房间导致侵略。在我们的实验室的以前的工作显示出那 rLj-RGD3,从 Lampetra 装饰用的梨树的口腔的腺分泌物的 recombinant RGD (ArgGlyAsp ) 毒素蛋白质,拥有反肿瘤活动。在这研究,我们证明 rLj-RGD3 压制了 TNF -- 在 786-0 房间(人的肾的癌房间) 的导致的 MMP-9 分泌物。在 TNF 上调查 rLj-RGD3 的规章的效果 -- 导致的 MMP-9 分泌物,我们预先对待有 rLj-RGD3 的房间。有趣地, rLj-RGD3 没在 MMP 的组成的分泌物上有重要效果。然而, rLj-RGD3 的低集中减少了 TNF -- 导致的 MMP-9 分泌物。功能的研究表明 rLj-RGD3 导致了 apoptosis 并且显著地禁止了 786-0 房间的增长,迁居,和侵略。而且,在房间的肌动朊建筑学与 rLj-RGD3 预先对待被聚集并且瓦解。我们的调查结果建议 rLj-RGD3 可以在肾的癌症被用作潜在的药治疗。 | Minli Jin Rong Xiao Jihong Wang Xin Liu Yu Liu Zhuang Xue Li Lv Yuanyuan Zheng Qingwei Li | 2013 | Acta Biochimica et Biophysica Sinica2013，45，5： | 2 |
| 3 | Safety prediction of high speed face milling cutter with indexable inserts显示文摘 | Jiang Bin Zheng Minli Xu Fang | 2008 | Key Engineering Materials2008，，： | 1 |
| 4 | GENERALIZED AUGMENTED LAGRANGIAN-SOR ITERATION METHOD FOR SADDLE-POINT SYSTEMS ARISING FROM DISTRIBUTED CONTROL PROBLEMS*显示文摘在这份报纸,一个概括扩充 Lagrangian 连续的在松驰上(GAL-SOR ) 重复方法为解决从分布式的控制问题产生的僵绳点系统被介绍。GAL-SOR 方法的集中性质详细被学习。而且 0 < 1 并且 Q = 1/r 我,光谱为 preconditioned 矩阵的性质被分析。数字实验证明如果从分布式的控制问题的集体矩阵不对逆容易,规则化参数是很小的, GAL-SOR 重复方法能工作很好。 ' | Minli Zeng Guofeng Zhang Zhong Zheng | 2016 | Journal of Computational Mathematics2016，34，2： | 1 |
| 5 | The role of immune cells in obesogenic memory显示文摘Obesity is a serious chronic disease and worldwide public health problem.According to data from the World Health Organization(WHO),more than 650 million adults in the world were obese and three times more individuals were overweight in 2016.Obesity is associated with type II diabetes,hepatic steatosis,cardiovascular diseases,systemic chronic inflammation,and at least 13 types of cancer.Unfortunately,few effective remedies are available for obesity.The major problem is that most patients suffer from weight regain 2–3 years after obesity treatments,such as obesity drugs,lifestyle interventions(including exercise,diet restrictions,and diet modification),and bariatric surgery.Along with weight regain,most of the initial beneficial changes in metabolomic and transcriptomic profiles dissipate,including insulin sensitivity,the level of adipokines and blood cholesterol.This phenomenon has been defined as“obesogenic memory”.1,2 Obesogenic memory causes repeated weight loss and gain along with obesity therapy,which is called“weight cycling”,leading to a worse healthy status than would result from simple obesity.3,4. | Minli Sun Shang Zheng Xiang Gao Zhaoyu Lin | 2020 | Cellular & Molecular Immunology2020，17，8： | 0 |
| 6 | EVA2.0:Investigating Open-domain Chinese Dialogue Systems with Large-scale Pre-training显示文摘Large-scale pre-training has shown remarkable performance in building open-domain dialogue systems.However,previous works mainly focus on showing and evaluating the conversational performance of the released dialogue model,ignoring the discussion of some key factors towards a powerful human-like chatbot,especially in Chinese scenarios.In this paper,we conduct extensive experiments to investigate these under-explored factors,including data quality control,model architecture designs,training approaches,and decoding strategies.We propose EVA2.0,a large-scale pre-trained open-domain Chinese dialogue model with 2.8 billion parameters,and will make our models and codes publicly available.Automatic and human evaluations show that EVA2.0 significantly outperforms other open-source counterparts.We also discuss the limitations of this work by presenting some failure cases and pose some future research directions on large-scale Chinese open-domain dialogue systems. | Yuxian Gu Jiaxin Wen Hao Sun Yi Song Pei Ke Chujie Zheng Zheng Zhang Jianzhu Yao Lei Liu Xiaoyan Zhu Minlie Huang | 2023 | Machine Intelligence Research2023，20，2： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员