Search Results - "Zhou, Pingyi"

Scalable tag recommendation for software information sites by Pingyi Zhou, Jin Liu, Zijiang Yang, Guangyou Zhou

“…Software developers can search, share and learn development experience, solutions, bug fixes and open source projects in software information sites such as…”
Get full text

Is deep learning better than traditional approaches in tag recommendation for software information sites? by Zhou, Pingyi, Liu, Jin, Liu, Xiao, Yang, Zijiang, Grundy, John

“…Inspired by the success of deep learning in other domains, this new technique been gaining widespread recent interest in being applied to diverse data analysis…”
Get full text

Effect of modified coal tar pitch addition on the microstructure and properties of Al2O3–SiC–C castables for solid waste incinerators by Wang, Shijie, Zhou, Pingyi, Liu, Xin, Cui, Junyan, Liu, Xinhong, Zhang, Shaowei, Jia, Quanli

“…Al2O3–SiC–C (ASC) castables were performed using brown alumina, SiC, ultrafine α-Al2O3, microsilica, Si powder, calcium aluminate cement and modified coal tar…”
Get full text

FastTagRec: fast tag recommendation for software information sites by Liu, Jin, Zhou, Pingyi, Yang, Zijiang, Liu, Xiao, Grundy, John

“…Software information sites such as StackOverflow and Freeecode enable information sharing and communication for developers around the world. To facilitate…”
Get full text

Effect of firing atmosphere on the microstructure and properties of Al2O3–SiC–C castables by Zhou, Pingyi, Qiu, Xin, Luo, Zhongtao, Liu, Xinhong, Zhang, Shaowei, Jia, Quanli

“…Al2O3–SiC–C (ASC) castables were performed using brown fused alumina as aggregates, silicon carbide, white fused alumina, ultrafine α-Al2O3, microsilica,…”
Get full text

Effect of Carbon Black Content and Firing Atmosphere on the Properties and Microstructure of Al2O3-SiC-C Castables by Jia, Quanli, Chen, Jing, He, Mantang, Sang, Mengyang, Zhou, Pingyi, Ma, Haoxuan

“…Al2O3-SiC-C (ASC) castables containing spherical asphalt are widely utilized in high-temperature metallurgical furnaces because of their good abrasive…”
Get full text

History, Present and Future: Enhancing Dialogue Generation with Few-Shot History-Future Prompt by Wang, Yihe, Li, Yitong, Wang, Yasheng, Mi, Fei, Zhou, Pingyi, Liu, Jin, Jiang, Xin, Liu, Qun

“…Dialogue history and response in open-domain dialogue are loosely coupled. Generating informative responses solely based on the original dialogue history is…”
Get full text

Automatically Constructing of Association Semantic Link Enabled Subject Cognitive Mapping by Pingyi Zhou, Jin Liu, Xianzhao Yang, Xu Chen, Shunxiang Zhang

“…Knowledge service such as the subject cognitive mapping plays an important role in effective online subject learning, skill training and subject resource…”
Get full text

Automatically constructing course dependence graph based on association semantic link model by Zhou, Pingyi, Liu, Jin, Yang, Xianzhao, Cui, Xiaohui, Chang, Liang, Zhang, Shunxiang

“…Course dependence graph of subject can provide an important reference model for the automatic arrangement for subject teaching plan, effective online subject…”
Get full text

Extending Context Window of Large Language Models via Semantic Compression by Fei, Weizhi, Niu, Xueyan, Zhou, Pingyi, Hou, Lu, Bai, Bo, Deng, Lei, Han, Wei

“…Transformer-based Large Language Models (LLMs) often impose limitations on the length of the text input to ensure the generation of fluent and relevant…”
Get full text

XL3M: A Training-free Framework for LLM Length Extension Based on Segment-wise Inference by Wang, Shengnan, Bai, Youhui, Zhang, Lin, Zhou, Pingyi, Zhao, Shixiong, Zhang, Gong, Wang, Sen, Chen, Renhai, Xu, Hua, Sun, Hongwei

“…Length generalization failure problem, namely the large language model (LLM) fails to generalize to texts longer than its maximum training length, greatly…”
Get full text

MultiCoder: Multi-Programming-Lingual Pre-Training for Low-Resource Code Completion by Gong, Zi, Guo, Yinpeng, Zhou, Pingyi, Gao, Cuiyun, Wang, Yasheng, Xu, Zenglin

“…Code completion is a valuable topic in both academia and industry. Recently, large-scale mono-programming-lingual (MonoPL) pre-training models have been…”
Get full text

CODE-MVP: Learning to Represent Source Code from Multiple Views with Contrastive Pre-Training by Wang, Xin, Wang, Yasheng, Wan, Yao, Wang, Jiawei, Zhou, Pingyi, Li, Li, Wu, Hao, Liu, Jin

“…Recent years have witnessed increasing interest in code representation learning, which aims to represent the semantics of source code into distributed vectors…”
Get full text

Compilable Neural Code Generation with Compiler Feedback by Wang, Xin, Wang, Yasheng, Wan, Yao, Mi, Fei, Li, Yitong, Zhou, Pingyi, Liu, Jin, Wu, Hao, Jiang, Xin, Liu, Qun

“…Automatically generating compilable programs with (or without) natural language descriptions has always been a touchstone problem for computational linguistics…”
Get full text

Pan More Gold from the Sand: Refining Open-domain Dialogue Training with Noisy Self-Retrieval Generation by Wang, Yihe, Li, Yitong, Wang, Yasheng, Mi, Fei, Zhou, Pingyi, Wang, Xin, Liu, Jin, Jiang, Xin, Liu, Qun

“…Real human conversation data are complicated, heterogeneous, and noisy, from which building open-domain dialogue systems remains a challenging task. In fact,…”
Get full text

SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation by Wang, Xin, Wang, Yasheng, Mi, Fei, Zhou, Pingyi, Wan, Yao, Liu, Xiao, Li, Li, Wu, Hao, Liu, Jin, Jiang, Xin

“…Code representation learning, which aims to encode the semantics of source code into distributed vectors, plays an important role in recent deep-learning-based…”
Get full text

PanGu-{\Sigma}: Towards Trillion Parameter Language Model with Sparse Heterogeneous Computing by Ren, Xiaozhe, Zhou, Pingyi, Meng, Xinfan, Huang, Xinjing, Wang, Yadao, Wang, Weichao, Li, Pengfei, Zhang, Xiaoda, Podolskiy, Alexander, Arshinov, Grigory, Bout, Andrey, Piontkovskaya, Irina, Wei, Jiansheng, Jiang, Xin, Su, Teng, Liu, Qun, Yao, Jun

“…The scaling of large language models has greatly improved natural language understanding, generation, and reasoning. In this work, we develop a system that…”
Get full text

PanGu-Coder: Program Synthesis with Function-Level Language Modeling by Christopoulou, Fenia, Lampouras, Gerasimos, Gritta, Milan, Zhang, Guchun, Guo, Yinpeng, Li, Zhongqi, Zhang, Qi, Xiao, Meng, Shen, Bo, Li, Lin, Yu, Hao, Yan, Li, Zhou, Pingyi, Wang, Xin, Ma, Yuchi, Iacobacci, Ignacio, Wang, Yasheng, Liang, Guangtai, Wei, Jiansheng, Jiang, Xin, Wang, Qianxiang, Liu, Qun

“…We present PanGu-Coder, a pretrained decoder-only language model adopting the PanGu-Alpha architecture for text-to-code generation, i.e. the synthesis of…”
Get full text

Preparation, characterization and hydrodesulfurization performances of Co-Ni_2P/SBA- 15 catalysts by Zhou-jun Wang Pingyi Wu Ling Lan Kunhong Liu Yaqiong Hu Shengfu Jia

“…A series of Co-Ni_2P/SBA-15 catalysts with various Co contents, Ni_2P contents and P/Ni molar ratios were prepared by impregnating nickel nitrate, diammonium…”
Get full text