99 citations · 205 across the 10 of their papers we have counts for
10 papers
HoME: Hierarchy of Multi-Gate Experts for Multi-Task Learning at Kuaishou
Xu Wang, Jiangxia Cao, Zhiyi Fu +2
In this paper, we present the practical problems and the lessons learned at short-video services from Kuaishou. In industry, a widely-used multi-task framework is the Mixture-of-Ex…
TWIN: TWo-stage Interest Network for Lifelong User Behavior Modeling in CTR Prediction at Kuaishou
Jianxin Chang, Chenbin Zhang, Zhiyi Fu +8
Life-long user behavior modeling, i.e., extracting a user's hidden interests from rich historical behaviors in months or even years, plays a central role in modern CTR prediction s…
CodeEditor: Learning to Edit Source Code with Pre-trained Models
Jia Li, Ge Li, Zhuo Li +4
Developers often perform repetitive code editing activities for various reasons (e.g., code refactoring) during software development. Pre-trained code editing models have achieved…
Non-autoregressive Model for Full-line Code Completion
Fang Liu, Zhiyi Fu, Ge Li +3
Code completion tools are frequently used by software developers to accelerate software development by suggesting the following code elements. Completing a sequence of code tokens…
Contextual Representation Learning beyond Masked Language Modeling
Zhiyi Fu, Wangchunshu Zhou, Jingjing Xu +2
How do masked language models (MLMs) such as BERT learn contextual representations? In this work, we analyze the learning dynamics of MLMs. We find that MLMs adopt sampled embeddin…
Learning to Recommend Method Names with Global Context
Fang Liu, Ge Li, Zhiyi Fu +3
In programming, the names for the program entities, especially for the methods, are the intuitive characteristic for understanding the functionality of the code. To ensure the read…
A Survey on Green Deep Learning
Jingjing Xu, Wangchunshu Zhou, Zhiyi Fu +2
In recent years, larger and deeper models are springing up and continuously pushing state-of-the-art (SOTA) results across various fields like natural language processing (NLP) and…
TUTA: Tree-based Transformers for Generally Structured Table Pre-training
Zhiruo Wang, Haoyu Dong, Ran Jia +4
Tables are widely used with various structures to organize and present data. Recent attempts on table understanding mainly focus on relational tables, yet overlook to other common…
Code Generation as a Dual Task of Code Summarization
Bolin Wei, Ge Li, Xin Xia +2
Code summarization (CS) and code generation (CG) are two crucial tasks in the field of automatic software development. Various neural network-based approaches are proposed to solve…
A Self-Attentional Neural Architecture for Code Completion with Multi-Task Learning
Fang Liu, Ge Li, Bolin Wei +3
Code completion, one of the most useful features in the Integrated Development Environments (IDEs), can accelerate software development by suggesting the libraries, APIs, and metho…