Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 24 for “"code completion"”.
-
Context-Sensitive Code Completion
… using those APIs, this thesis focuses on the code completion feature of modern integrated development environments (IDEs). As a developer types code, a code completion system offers a list of completion proposals through a popup menu to navigate and select. This research aims to improve the …
-
AI Supported Software Development: Moving Beyond Code Completion
… and successes of large language models for code, such as Copilot/Codex (Github/OpenAI) and AlphaCode (DeepMind). Above-average human performance on programming challenges is now possible. However, software development is much more than solving programming contests. Moving beyond code …
-
Exploring the design space of AI based code completion engines
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms
-
Learning APIs through Mining Code Snippet Examples
… APIs for effectively using them in their codebase. However, APIs are difficult to learn as they are large in numbers and are not properly documented and the documentation contains a lot of text to remember. To support developers learning and using those APIs, this thesis focuses three …
-
Learning APIs through Mining Code Snippet Examples
… APIs for effectively using them in their codebase. However, APIs are difficult to learn as they are large in numbers and are not properly documented and the documentation contains a lot of text to remember. To support developers learning and using those APIs, this thesis focuses three …
-
Program Synthesis Without Full Specifications for Novel Applications
… tasks to show the breadth of our methodology: code completion, end-user programming-by-example for data transformations, and feedback for introductory programming assignments. For each of these tasks, we develop an interaction model and program synthesis algorithm together to best support the …
-
Intelligent Software Tooling For Improving Software Development
… impact on the world such as generating code and test cases, detecting bugs, question and answering, etc. The success of Deep Learning (DL) over the past decade has shown huge advancements in automation across many domains, including Software Development processes. One of the main reasons …
-
A study on the performance of statistical machine translation and neural machine translation for prefix resolution in software engineering
… By achieving the accuracy from 65% to 90% for code tokens generation of 1000 Github code corpus, we show the potential of using MT for code completion at token level.
-
Autocompletion Without Static Typing
Code completion systems act both as a way to decrease typing and as a way to easily access documentation, both implicit and explicit. The former is typically done by completing known variable or function names, while the latter is done by providing a list of possible completions or by providing …
-
HAnS: IDE-based editing support for embedded feature annotations
… for embedding feature annotations in source code during development, as embedding feature annotations is shown to be a cheap and reliable way to keep track of feature locations. To implement the plugin, a design science methodology was adopted where we performed user studies to find what …
-
Recognizing and understanding user behaviors from screencasts
… many applications such as intelligent bug fix, code completion and knowledge recommendation for developers. Such technique can be extended to more general knowledge worker environment, in which users have to manipulate devices according to specific guidelines. Existing works rely heavily on …
-
Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications
… the backend for various applications, including code completion tools and AI-powered search engines. Unlike traditional LLM usage where users directly query the model, LLM-integrated applications act as middleware, refining user inputs with domain-specific knowledge. This approach enhances the …
-
Building Representations and Quantifying Uncertainty With Pairwise Consistency
… a model can be used to build uncertainty-aware code completion suggestions. Finally, we study the problem of identifying the amount of uncertainty in a generative model when it imitates a ground-truth process, and show that the predicted correlations between independently-generated data points …
-
Explaining software faults in source code
… Segundo, utilizando o modelo generativo CodeGPT, abordamos APR como um desafio de code completion, gerando linhas de correção candidatas, com base num ficheiro defeituoso e número de linha, através de um processo de várias etapas que envolve parsing do código, geração de sequências de …
-
Evaluating the effectiveness and efficiency of Parsons problems and dynamically adaptive parsons problems as a type of low cognitive load practice problem
… One way to reduce learning time is to use a completion task. Parsons problems are a type of code completion problem in which the learner must place blocks of correct, but mixed up, code in the correct order. Parsons problems can also have distractor blocks, which are not needed in a correct …
-
Trojan Detection in Large Language Models of Code
… is about defending large language models of code (Code-LLMs) against trojan attacks. Code-LLMs are widely used in software development for tasks such as vulnerability detection, clone detection, code completion, and code summarization. Popular platforms that use AI-assisted software …
-
Combining static analysis with deep learning for type inference and code editing
… treat programs as sequences of tokens and encode only local syntactic information. While this approach has achieved impressive results on tasks such as code autocompletion and program synthesis, many other tasks require analyzing programs at the project level. In this thesis, we propose …
-
Elide : an interactive development environment for Erasmus language
… features included in ELIDE are syntax coloring, Code folding, Code completion, Brace matching, Coding tips, Indentation and Annotations. ELIDE is capable of adding more features later in case there is a need. Furthermore ELIDE can be used for an easy integration of editing and visualising support …
-
Towards multi-dimensional integrated development environments for improved productivity
… developers' inherent understandings of their code and learned skills in software development processes. This dissertation presents our research effort in creating a new class of plug-ins that addresses these shortcomings without hampering developers' productivity. Our approach achieves this …
-
Machine learning for executable code in software testing and verification
… significant manual effort to write and maintain code artifacts needed for testing and verification, i.e., tests and proofs. With the pressure for developing software in limited time, developers usually write tests and proofs much later than the code under test/verification, which leaves room for …
Page 1 of 2