相关论文: INSPECT: Intrinsic and Systematic Probing Evaluati…

Generative pre-trained models power intelligent software features used by millions of users controlled by developer-written natural language prompts. Despite the impact of prompt-powered software, little is known about its development…

Research at the intersection of machine learning, programming languages, and software engineering has recently taken important steps in proposing learnable probabilistic models of source code that exploit code's abundance of patterns. In…

Pre-trained language models have been shown to encode linguistic structures, e.g. dependency and constituency parse trees, in their embeddings while being trained on unsupervised loss functions like masked language modeling. Some doubts…

Vulnerability analysis is crucial for software security. This work focuses on using pre-training techniques to enhance the understanding of vulnerable code and boost vulnerability analysis. The code understanding ability of a pre-trained…

Language models have become nearly ubiquitous in natural language processing applications achieving state-of-the-art results in many tasks including prosody. As the model design does not define predetermined linguistic targets during…

In this paper we investigate the linguistic knowledge learned by a Neural Language Model (NLM) before and after a fine-tuning process and how this knowledge affects its predictions during several classification problems. We use a wide set…

Pre-trained Language Model (PLM) has become a representative foundation model in the natural language processing field. Most PLMs are trained with linguistic-agnostic pre-training tasks on the surface form of the text, such as the masked…

Vulnerability detection is garnering increasing attention in software engineering, since code vulnerabilities possibly pose significant security. Recently, reusing various code pre-trained models has become common for code embedding without…

For most natural language processing tasks, the dominant practice is to finetune large pretrained transformer models (e.g., BERT) using smaller downstream datasets. Despite the success of this approach, it remains unclear to what extent…

The advancements in machine learning techniques have encouraged researchers to apply these techniques to a myriad of software engineering tasks that use source code analysis, such as testing and vulnerability detection. Such a large number…

Neural networks have in recent years shown promise for helping software engineers write programs and even formally verify them. While semantic information plays a crucial part in these processes, it remains unclear to what degree popular…

BERT (Bidirectional Encoder Representations from Transformers) and related pre-trained Transformers have provided large gains across many language understanding tasks, achieving a new state-of-the-art (SOTA). BERT is pre-trained on two…

Heavily pre-trained transformer models such as BERT have recently shown to be remarkably powerful at language modelling by achieving impressive results on numerous downstream tasks. It has also been shown that they are able to implicitly…

Pre-trained Programming Language Models (PPLMs) achieved many recent states of the art results for many code-related software engineering tasks. Though some studies use data flow or propose tree-based models that utilize Abstract Syntax…

Transformer-based models have pushed state of the art in many areas of NLP, but our understanding of what is behind their success is still limited. This paper is the first survey of over 150 studies of the popular BERT model. We review the…

Introductory programming courses often rely on small code-writing exercises that have clearly specified problem statements. This limits opportunities for students to practice how to clarify ambiguous requirements -- a critical skill in…

APIs (Application Programming Interfaces) are reusable software libraries and are building blocks for modern rapid software development. Previous research shows that programmers frequently share and search for reviews of APIs on the…

The term "Code Mixed" refers to the use of more than one language in the same text. This phenomenon is predominantly observed on social media platforms, with an increasing amount of adaptation as time goes on. It is critical to detect…

In the past couple of decades, significant research efforts are devoted to the prediction of software bugs. However, most existing work in this domain treats all bugs the same, which is not the case in practice. It is important for a defect…

The capability of accurately determining code similarity is crucial in many tasks related to software development. For example, it might be essential to identify code duplicates for performing software maintenance. This research introduces…