http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Zeyu Ding,Armagan Elibol,Nak Young Chong 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11
Multi-turn dialogue is the major manifestation of a conversation. Compared with single-turn dialogue, response selection is more complex as the context varies. We stress the importance of dialogue history and apply the pre-trained model BERT to assign proper weight to each utterance of a dialogue. Previous works take all the dialogue history as context to measure the matching degree of a context-response pair, causing the quadratic computational cost and truncation of longer sequences exceeding the length limitation of BERT. We propose a sentence-based method to deal with the aforementioned problems, obtaining the sentence embedding of a single unit utterance of dialogue and forming a classification token of a context-response pair. We discuss how to obtain a sentence embedding with high quality and to design the input representations in response selection. The results show that the average of the first-last layer output exhibits the best performance for obtaining a sentence representation. The proposed method, concatenating the sentence embeddings of context with the token embeddings of response candidates, is nearly on a par with the token embedding based SOTA method. Notably, the processable length of dialogue history is enlarged about ten times with a low computational cost, potentially reducing chatbot response time and inspiring user engagement.
Similar Hand Gesture Recognition by Automatically Extracting Distinctive Features
Zeyu Ding,Yanmei Chen,Xinyu Wu,Yen-Lun Chen 제어·로봇·시스템학회 2017 International Journal of Control, Automation, and Vol.15 No.4
With the flourish development of computer vision technology, hand gesture recognition plays a moreand more vital role in human-computer interaction for its convenient and nonverbal communication. However,confusion caused by similar gestures brings inherent errors when considering enough meaningful gestures in thedatabase. In this paper, an automatic feature extraction for similar gesture recognition is proposed with respect toconfusion arising in similar gestures. Except the orientation feature, four additional innovative features are extractedto distinguish all the similar gestures remarkably in the experimental database containing 10 numbers and 26 letters. Compared with the conventional method that a couple of similar gestures are extracted as a specific feature, theproposed method distinguishes similar gestures with automatic distinctive feature extraction. Experimental resultsshow high recognition rate and versatility of the proposed method.
MiR-200c-3p aggravates gastric cell carcinoma via KLF6
Wang Ying,Lu Kaijuan,Li Weibing,Wang Zhigang,Ding Jing,Zhu Zeyu,Li Zhipeng 한국유전학회 2021 Genes & Genomics Vol.43 No.11
Background Gastric cell carcinoma (GCC) is a common and high-incidence malignant gastrointestinal cancer that seriously threatens human life and safety. Evidences suggest that microRNAs (miRNAs) exhibit an essential role in regulating the occurrence and development of GCC, while the efects and possible mechanisms remain to be further explored. Objective This study was designed to explore whether miR-200c-3p exerted its functional role in the growth and metastasis of GCC, and investigate the possible mechanisms. Methods The expression levels of miR-200c-3p in GCC tissues and cell lines were detected by qRT-PCR analysis. The functional role of miR-200c-3p in the viability, proliferation, migration and invasion of GCC cells were evaluated by CCK-8, EdU, wound healing and Transwell assays. In addition, the candidate targets of miR-200c-3p was predicted and confrmed by dual-luciferase reporter assay. Moreover, the relationship between miR-200c-3p and target (Krüppel like factor 6, KLF6) was assessed by qRT-PCR and western blot assays. Besides, the expression levels of KLF6 in GCC cells were determined by qRT-PCR and western blot assays. Furthermore, the role of KLF6 in the viability, proliferation, migration and invasion of GCC cells mediated with miR-200c-3p mimics was evaluated by CCK-8, EdU, wound healing and Transwell assays. Results In the present study, a new tumor promoting function of miR-200c-3p was disclosed in GCC. We found that the expression of miR-200c-3p was obviously increased in clinic GCC tissues and cell lines. In addition, down-regulation of miR-200c-3p suppressed cell viability, proliferation, migration, and invasion in GCC cells. Moreover, KLF6 was verifed as a direct target of miR-200c-3p by binding its 3’-UTR. Additionally, KLF6 was remarkably decreased and was negatively associated with the miR-200c-3p expression in GCC cell lines. Furthermore, over-expression of KLF6 retarded the efects of miR-200c-3p on the growth and metastasis of GCC cell lines. Conclusions MiR-200c-3p potentially played a tumor-promoting role in the occurrence and development of GCC, which may be achieved by targeting KLF6.