Intelligent Code Completion with Bayesian Networks

By Sebastian Proksch, Johannes Lerch, Mira Mezini. 2015

92 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems, Management Science and Operations Research, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Information Systems

In Management Science and Operations Research

In Natural Language Processing

Citations in the corpus

A Survey of Machine Learning for Big Code and Naturalness (2017, methodology): “[159] use a directed graphical model to represent the context of an (incomplete) usage of an object to suggest a method invocation (viz.”
IntelliCode compose: code generation using transformer (2020, background): “A large number of intelligent code completion systems for both statically and dynamically typed languages have been proposed [6, 11, 41, 42].”
WILDS: A Benchmark of in-the-Wild Distribution Shifts (2020, neutral): “Code completion models—autocomplete tools used by programmers to suggest subsequent source code tokens, such as the names of API calls—are commonly used to reduce the effort of software development (Robbes & Lanza, 2008; Bruch et al., 2009; Nguyen & Nguyen, 2015; Proksch et al., 2015; Franks et al.,”
When Code Completion Fails: A Case Study on Real-World Completions (2019, methodology): “Other models have been proposed, both using natural language models (e.g., [4], [22], [23]) and traditional feature selection (e.g., [5]–[7]); we leave the analysis of such models to future work and provide our dataset to support such efforts.”
A Study of Visual Studio Usage in Practice (2016, methodology): “IDE Usage: The studies closest to ours are Murphy et al.’s study [1] on the usage of the Eclipse IDE for Java and Minelli et al.’s study [2] on the usage of the Pharo IDE for Smalltalk.”
Evaluating the evaluations of code recommender systems: A reality check (2016, methodology): “The prediction quality range reported by PBN for this dataset is lower than prediction qualities usually obtained in the literature, including our previous experience with PBN on Java SWT [22].”
Pythia: AI-assisted Code Completion System (2019, background): “A large number of intelligent code completion systems for both statically and dynamically typed languages have been proposed in the literature [4, 5, 2, 6, 7, 8].”
Code Prediction by Feeding Trees to Transformers (2020, methodology): “ally these names were organized alphabetically, though people have tried sorting them by occurrence frequency or even applying per-user Bayesian optimization to rank the list (DâĂŹSouza et al., 2016, Proksch et al., 2015). However, a type-based autocomplete is not very effective. For example, as men”