Search Results for author:
Found 16 papers, 9 papers with code
Dynamic Retrieval-Augmented Generation
Our approach achieves several targets: (1) lifting the length limitations of the context window, saving on the prompt size; (2) allowing huge expansion of the number of retrieval entities available for the context; (3) alleviating the problem of misspelling or failing to find relevant entity names.
From Commit Message Generation to History-Aware Commit Message Completion
We use this dataset to evaluate the completion setting and the usefulness of the historical context for state-of-the-art CMG models and GPT-3. 5-turbo.
Judging Adam: Studying the Performance of Optimization Methods on ML4SE Tasks
In this work, we test the performance of various optimizers on deep learning models for source code and find that the choice of an optimizer can have a significant impact on the model quality, with up to two-fold score differences between some of the relatively well-performing optimizers.
Out of the BLEU: how should we assess quality of the Code Generation models?
Despite all that, minimal differences in the metric scores have been used in recent papers to claim superiority of some code generation models over the others.
Evaluation of Contrastive Learning with Various Code Representations for Code Clone Detection
The first task is code clone detection, which we evaluate on the POJ-104 dataset containing implementations of 104 algorithms.
Evaluating the Impact of Source Code Parsers on ML4SE Models
Even though the process of extracting ASTs from code can be done with different parsers, the impact of choosing a parser on the final model quality remains unstudied.
Assessing Project-Level Fine-Tuning of ML4SE Models
We evaluate three models of different complexity and compare their quality in three settings: trained on a large dataset of Java projects, further fine-tuned on the data from a particular project, and trained from scratch on this data.
All You Need Is Logs: Improving Code Completion by Learning from Anonymous IDE Usage Logs
We used the logs to collect a dataset of code completions from users, and employed it to train a ranking CatBoost model.
On the Transferability of Pre-trained Language Models for Low-Resource Programming Languages
Furthermore, some programming languages are inherently different and code written in one language usually cannot be interchanged with the others, i. e., Ruby and Java code possess very different structure.
DapStep: Deep Assignee Prediction for Stack Trace Error rePresentation
In this work, we explore the applicability of existing solutions for the bug triage problem when stack traces are used as the main data source of bug reports.
Unsupervised Learning of General-Purpose Embeddings for Code Changes
As for the commit message generation, our model demonstrated the same results as supervised models trained for this specific task, which indicates that it can encode code changes well and can be improved in the future by pre-training on a larger dataset of easily gathered code changes.
PSIMiner: A Tool for Mining Rich Abstract Syntax Trees from Code
PSI trees contain code syntax trees as well as functions to work with them, and therefore can be used to enrich code representation using static analysis algorithms of modern IDEs.
TaskTracker-tool: a Toolkit for Tracking of Code Snapshots and Activity Data During Solution of Programming Tasks
To validate and showcase the toolkit, we present a dataset collected by our tools.
Software Engineering D.2.2; K.3.2
Sosed: a tool for finding similar software projects
We use a dataset of 9 million GitHub projects as a reference search base.
Software Engineering
Using Large-Scale Anomaly Detection on Code to Improve Kotlin Compiler
In this work, we apply anomaly detection to source code and bytecode to facilitate the development of a programming language and its compiler.
Building Implicit Vector Representations of Individual Coding Style
With the goal of facilitating team collaboration, we propose a new approach to building vector representations of individual developers by capturing their individual contribution style, or coding style.
Software Engineering Social and Information Networks
