相关论文: The test set for the TransCoder system

Code translation transforms code between programming languages while preserving functionality, which is critical in software development and maintenance. While traditional learning-based code translation methods have limited effectiveness…

Multilingual translation suffers from computational redundancy, especially when translating into multiple languages simultaneously. In addition, translation quality can suffer for low-resource languages. To address this, we introduce…

Static program analysis tools are often required to work with only a small part of a program's source code, either due to the unavailability of the entire program or the lack of need to analyze the complete code. This makes it challenging…

Machine transliteration is the process of automatically transforming the script of a word from a source language to a target language, while preserving pronunciation. Sequence to sequence learning has recently emerged as a new paradigm in…

Code completion is a key feature of Integrated Development Environments (IDEs), aimed at predicting the next tokens a developer is likely to write, helping them write code faster and with less effort. Modern code completion approaches are…

Training LLMs for code-related tasks typically depends on high-quality code-documentation pairs, which are costly to curate and often scarce for niche programming languages. We introduce BatCoder, a self-supervised reinforcement learning…

Neural machine translation represents an exciting leap forward in translation quality. But what longstanding weaknesses does it resolve, and which remain? We address these questions with a challenge set approach to translation evaluation…

Knowledge-based systems are suitable for realizing advanced functions that require domain-specific expert knowledge, while knowledge representation languages and their supporting environments are essential for realizing such systems.…

The JUNIPER project is developing a framework for the construction of large-scale distributed systems in which execution time bounds can be guaranteed. Part of this work involves the automatic implementation of input Java code on FPGAs,…

Automatically generating source code from natural language descriptions has been a growing field of research in recent years. However, current large-scale code generation models often encounter difficulties when selecting appropriate APIs…

The introduction of large language models has significantly advanced code generation. However, open-source models often lack the execution capabilities and iterative refinement of advanced systems like the GPT-4 Code Interpreter. To address…

With the advent of numerous languages it is difficult to realize the edge of one language in a particular scope over another one. We are making an effort, realizing these few issues and comparing some main stream languages like Java, Scala,…

C/C++ is a prevalent programming language. Yet, it suffers from significant memory and thread-safety issues. Recent studies have explored automated translation of C/C++ to safer languages, such as Rust. However, these studies focused mostly…

The authors' "metatools" are a collection of tools for generic programming. This includes generating Java sources from mathematically well-founded specifications, as well as the creation of strictly typed document object models for XML…

In managed languages, serialization of objects is typically done in bespoke binary formats such as Protobuf, or markup languages such as XML or JSON. The major limitation of these formats is readability. Human developers cannot read binary…

JSON (JavaScript Object Notation) is a data encoding that allows structured data to be used in a standardized and straightforward manner across systems. Schemas for JSON-formatted data can be constructed using the JSON Schema standard,…

In recent years, the application of large language models (LLMs) to code-related tasks has gained significant attention. However, existing evaluation benchmarks often focus on limited scenarios, such as code generation or completion, which…

Transformer becomes the state-of-the-art translation model, while it is not well studied how each intermediate component contributes to the model performance, which poses significant challenges for designing optimal architectures. In this…

With the recent focus on Large Language Models (LLMs), both StarCoder (Li et al., 2023) and Code Llama (Rozi\`ere et al., 2023) have demonstrated remarkable performance in code generation. However, there is still a need for improvement in…

We describe a successful attempt to formally verify a simple genetic algorithm written in Java. To this end, we compare several formal verification tools designed for Java, and select Krakatoa as the most appropriate for the task. Based on…