An Empirical Analysis of InCoder on the Statement Prediction Task

Bachelor thesis (2022)

Authors

F.N.M. van der Heijden Electrical Engineering, Mathematics and Computer Science

Contributors

M. Izadi Software Engineering - (mentor)

A. van Deursen Software Technology (mentor)

A. Lukina Algorithmics - (graduation committee member)

Faculty

Electrical Engineering, Mathematics and Computer Science, Electrical Engineering, Mathematics and Computer Science

Code completion Incoder Statement completion Empirical analysis

To reference this document use:

http://resolver.tudelft.nl/uuid:69bb797f-4a62-4fef-afe8-1d9492b8d28e

More Info

expand_more

Published Date

24-06-2022

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Abstract

Automatic code completions are a widely used feature when programming code efﬁciently. These completions can be made by various code language models, and these can be differentiated in three categories: single token completion, statement (line) completion and block completions. These completions, and in particular statement predictions are usually created using only the left context, missing key information and context on the other side. InCoder, a novel state of the art model is capable of using both contexts. In this study we aim to show the impact of using both contexts in statement completions. The results show that on average, an improvement of 9.9% exact match and similar results for Edit Similarity, BLEU-4, ROUGE-L F1, and METEOR when using both contexts instead of only the left context.

Files

Main.pdf

(pdf | 0.53 Mb)