285 citations · 1.2k across the 36 of their papers we have counts for
36 papers
EditSum: A Retrieve-and-Edit Framework for Source Code Summarization
Jia Li, Yongmin Li, Ge Li +3
Existing studies show that code summaries help developers understand and maintain source code. Unfortunately, these summaries are often missing or outdated in software projects. Co…
EvEval: A Comprehensive Evaluation of Event Semantics for Large Language Models
Zhengwei Tao, Zhi Jin, Xiaoying Bai +4
Events serve as fundamental units of occurrence within various contexts. The processing of event semantics in textual information forms the basis of numerous natural language proce…
Precise Learning of Source Code Contextual Semantics via Hierarchical Dependence Structure and Graph Attention Networks
Zhehao Zhao, Bo Yang, Ge Li +2
Deep learning is being used extensively in a variety of software engineering tasks, e.g., program classification and defect prediction. Although the technique eliminates the requir…
A Meta Reinforcement Learning-based Approach for Self-Adaptive System
Mingyue Zhang, Jialong Li, Haiyan Zhao +3
A self-learning adaptive system (SLAS) uses machine learning to enable and enhance its adaptability. Such systems are expected to perform well in dynamic situations. For learning h…
Modular Tree Network for Source Code Representation Learning
Wenhan Wang, Ge Li, Sijie Shen +2
Learning representation for source code is a foundation of many program analysis tasks. In recent years, neural networks have already shown success in this area, but most existing…
Massive Self-Assembly in Grid Environments
Wenjie Chu, Wei Zhang, Haiyan Zhao +2
Self-assembly plays an essential role in many natural processes, involving the formation and evolution of living or non-living structures, and shows potential applications in many…
Multi-task Learning based Pre-trained Language Model for Code Completion
Fang Liu, Ge Li, Yunfei Zhao +1
Code completion is one of the most useful features in the Integrated Development Environments (IDEs), which can accelerate software development by suggesting the next probable toke…
Learning to Represent Programs with Heterogeneous Graphs
Kechi Zhang, Wenhan Wang, Huangzhao Zhang +2
Program source code contains complex structure information, which can be represented in structured data forms like trees or graphs. To acquire the structural information in source…
Retrieve and Refine: Exemplar-based Neural Comment Generation
Bolin Wei, Yongmin Li, Ge Li +2
Code comment generation which aims to automatically generate natural language descriptions for source code, is a crucial task in the field of automatic software development. Tradit…
Towards Full-line Code Completion with Neural Language Models
Wenhan Wang, Sijie Shen, Ge Li +1
A code completion system suggests future code elements to developers given a partially-complete code snippet. Code completion is one of the most useful features in Integrated Devel…
Early Validation of Cyber-Physical Space Systems via Multi-Concerns Integration
Nianyu Li, Christos Tsigkanos, Zhi Jin +2
Cyber-physical space systems are engineered systems operating within physical space with design requirements that depend on space, e.g., regarding location or movement behavior. Th…
Detecting Code Clones with Graph Neural Networkand Flow-Augmented Abstract Syntax Tree
Wenhan Wang, Ge Li, Bo Ma +2
Code clones are semantically similar code fragments pairs that are syntactically similar or different. Detection of code clones can help to reduce the cost of software maintenance…
Modeling Programs Hierarchically with Stack-Augmented LSTM
Fang Liu, Lu Zhang, Zhi Jin
Programming language modeling has attracted extensive attention in recent years, and it plays an essential role in program processing fields. Statistical language models, which are…
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…
Solving Pictorial Jigsaw Puzzle by Stigmergy-inspired Internet-based Human Collective Intelligence
Bo Shen, Wei Zhang, Haiyan Zhao +2
The pictorial jigsaw (PJ) puzzle is a well-known leisure game for humans. Usually, a PJ puzzle game is played by one or several human players face-to-face in the physical space. In…
Why Do Neural Dialog Systems Generate Short and Meaningless Replies? A Comparison between Dialog and Translation
Bolin Wei, Shuai Lu, Lili Mou +4
This paper addresses the question: Why do neural dialog systems generate short and meaningless replies? We conjecture that, in a dialog system, an utterance may have multiple equal…
Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models
Zhao Meng, Lili Mou, Zhi Jin
Neural network-based dialog systems are attracting increasing attention in both academia and industry. Recently, researchers have begun to realize the importance of speaker modelin…
CodeSum: Translate Program Language to Natural Language
Xing Hu, Yuhan Wei, Ge Li +1
During software maintenance, programmers spend a lot of time on code comprehension. Reading comments is an effective way for programmers to reduce the reading and navigating time w…
Requirements-Driven Dynamic Adaptation to Mitigate Runtime Uncertainties for Self-Adaptive Systems
Zhuoqun Yang, Wei Zhang, Haiyan Zhao +1
Self-adaptive systems are capable of adjusting their behavior to cope with the changes in environment and itself. These changes may cause runtime uncertainty, which refers to the s…
Hierarchical RNN with Static Sentence-Level Attention for Text-Based Speaker Change Detection
Zhao Meng, Lili Mou, Zhi Jin
Speaker change detection (SCD) is an important task in dialog modeling. Our paper addresses the problem of text-based SCD, which differs from existing audio-based studies and is us…
Coupling Distributed and Symbolic Execution for Natural Language Queries
Lili Mou, Zhengdong Lu, Hang Li +1
Building neural networks to query a knowledge base (a table) with natural language is an emerging research topic in deep learning. An executor for table querying typically requires…
Compressing Neural Language Models by Sparse Word Representations
Yunchuan Chen, Lili Mou, Yan Xu +2
Neural networks are among the state-of-the-art techniques for language modeling. Existing neural language models typically map discrete words to distributed, dense vector represent…
Improved Knowledge Base Completion by Path-Augmented TransR Model
Wenhao Huang, Ge Li, Zhi Jin
Knowledge base completion aims to infer new relations from existing information. In this paper, we propose path-augmented TransR (PTransR) model to improve the accuracy of link pre…