Semantic similarity metrics for evaluating source code summarization
Source code summarization involves creating brief descriptions of source code in natural
language. These descriptions are a key component of software documentation such as …
language. These descriptions are a key component of software documentation such as …
Automated comment update: How far are we?
Code comments are key to program comprehension. When they are not consistent with the
code, maintenance is hindered. Yet developers often forget to update comments along with …
code, maintenance is hindered. Yet developers often forget to update comments along with …
Action word prediction for neural source code summarization
Source code summarization is the task of creating short, natural language descriptions of
source code. Code summarization is the backbone of much software documentation such as …
source code. Code summarization is the backbone of much software documentation such as …
Generating clarifying questions for query refinement in source code search
Z Eberhart, C McMillan - 2022 IEEE International Conference …, 2022 - ieeexplore.ieee.org
In source code search, a common information-seeking strategy involves providing a short
initial query with a broad meaning, and then iteratively refining the query using terms …
initial query with a broad meaning, and then iteratively refining the query using terms …
Dialogue management for interactive api search
Z Eberhart, C McMillan - 2021 IEEE International Conference …, 2021 - ieeexplore.ieee.org
API search involves finding components in an API that are relevant to a programming task.
For example, a programmer may need a function in a C library that opens a new network …
For example, a programmer may need a function in a C library that opens a new network …
Label Smoothing Improves Neural Source Code Summarization
Label smoothing is a regularization technique for neural networks. Normally neural models
are trained to an output distribution that is a vector with a single 1 for the correct prediction …
are trained to an output distribution that is a vector with a single 1 for the correct prediction …
代码注释自动生成方法综述
陈翔, 杨光, 崔展齐, 孟国柱, 王赞 - 软件学报, 2021 - jos.org.cn
在软件的开发和维护过程中, 与代码对应的注释经常存在缺失, 不足或者与代码实际内容不匹配
等问题, 但手工编写代码注释对开发人员来说费时费力, 且注释质量难以保证 …
等问题, 但手工编写代码注释对开发人员来说费时费力, 且注释质量难以保证 …
Meta Learning for Code Summarization
Source code summarization is the task of generating a high-level natural language
description for a segment of programming language code. Current neural models for the …
description for a segment of programming language code. Current neural models for the …
[PDF][PDF] Automatically Annotating Decompiled Code with Meaningful Names and Types
J Lacomis - 2023 - reports-archive.adm.cs.cmu.edu
Software reverse engineering is the problem of understanding the behavior of a program
without access to its source code. Since there is no source code, analysts must use the …
without access to its source code. Since there is no source code, analysts must use the …
[图书][B] Improved Source Code Summarization Using Context-Aware Inputs and Semantic Similarity Based Optimization
S Haque - 2022 - search.proquest.com
Software documentation largely consists of short, natural language summaries of the
subroutines in the software. These summaries help programmers quickly understand what a …
subroutines in the software. These summaries help programmers quickly understand what a …