DeepCode AI Fix: Fixing Security Vulnerabilities with Large Language Models

no code implementations • 19 Feb 2024 • Berkay Berabi, Alexey Gronskiy, Veselin Raychev, Gishor Sivanrupan, Victor Chibotaru, Martin Vechev

We show that the task is difficult as it requires the model to learn long-range code relationships, a task that inherently relies on extensive amounts of training data.

Code Repair Few-Shot Learning +1

TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer

1 code implementation • ICML 2021 • Berkay Berabi, Jingxuan He, Veselin Raychev, Martin Vechev

The problem of fixing errors in programs has attracted substantial interest over the years.

Code Generation Multi-Task Learning +1

Language-Independent Sentiment Analysis Using Subjectivity and Positional Information

no code implementations • 28 Nov 2019 • Veselin Raychev, Preslav Nakov

We describe a novel language-independent approach to the task of determining the polarity, positive or negative, of the author's opinion on a specific topic in natural language text.

Attribute General Classification +3

Learning a Static Analyzer from Data

no code implementations • 6 Nov 2016 • Pavol Bielik, Veselin Raychev, Martin Vechev

In this paper we present a new, automated approach for creating static analyzers: instead of manually providing the various inference rules of the analyzer, the key idea is to learn these rules from a dataset of programs.