Related papers: Incorporating Domain Knowledge through Task Augmen…

Code generation aims to automatically generate code snippets of specific programming language according to natural language descriptions. The continuous advancements in deep learning, particularly pre-trained models, have empowered the code…

Code generation aims to automatically generate a piece of code given an input natural language utterance. Currently, among dominant models, it is treated as a sequence-to-tree task, where a decoder outputs a sequence of actions…

Pre-trained language models have achieved promising success in code retrieval tasks, where a natural language documentation query is given to find the most relevant existing code snippet. However, existing models focus only on optimizing…

Preservation of domain knowledge from the source to target is crucial in any translation workflow. It is common in the translation industry to receive highly specialized projects, where there is hardly any parallel in-domain data. In such…

Advances in natural language processing, such as transfer learning from pre-trained language models, have impacted how models are trained for programming language tasks too. Previous research primarily explored code pre-training and…

Recent advancements in language modeling have enabled the translation of natural language into code, and the use of execution feedback to improve code generation. However, these methods often rely heavily on pre-existing test cases, which…

Pre-trained code models lead the era of code intelligence, with multiple models designed with impressive performance. However, one important problem, data augmentation for code data that automatically helps developers prepare training data…

Recent studies have demonstrated remarkable advancements in source code learning, which applies deep neural networks (DNNs) to tackle various software engineering tasks. Similar to other DNN-based domains, source code learning also requires…

Current generative knowledge graph construction approaches usually fail to capture structural knowledge by simply flattening natural language into serialized texts or a specification language. However, large generative language model…

Transformer-based pre-trained models have recently achieved great results in solving many software engineering tasks including automatic code completion which is a staple in a developer's toolkit. While many have striven to improve the…

Automatically generating human-readable text describing the functionality of a program is the intent of source code summarization. Although neural language models achieve significant performance in this field, they are limited by their…

With the rapid advancement of large language models (LLMs), extensive research has been conducted to investigate the code generation capabilities of LLMs. However, existing efforts primarily focus on general-domain tasks, leaving LLMs' code…

Code search is a widely used technique by developers during software development. It provides semantically similar implementations from a large code corpus to developers based on their queries. Existing techniques leverage deep learning…

Data augmentation is a ubiquitous technique for increasing the size of labeled training sets by leveraging task-specific data transformations that preserve class labels. While it is often easy for domain experts to specify individual…

Pre-trained language models for code (PLMCs) have gained attention in recent research. These models are pre-trained on large-scale datasets using multi-modal objectives. However, fine-tuning them requires extensive supervision and is…

Code completion is one of the most useful features in the Integrated Development Environments (IDEs), which can accelerate software development by suggesting the next probable token based on the contextual code in real-time. Recent studies…

In multilingual colloquial settings, it is a habitual occurrence to compose expressions of text or speech containing tokens or phrases of different languages, a phenomenon popularly known as code-switching or code-mixing (CMX). We present…

We propose task-adaptive tokenization as a way to adapt the generation pipeline to the specifics of a downstream task and enhance long-form generation in mental health. Inspired by insights from cognitive science, our task-adaptive…

Open-domain code generation aims to generate code in a general-purpose programming language (such as Python) from natural language (NL) intents. Motivated by the intuition that developers usually retrieve resources on the web when writing…

Code pre-trained models (CodePTMs) have recently demonstrated a solid capacity to process various software intelligence tasks, e.g., code clone detection, code translation, and code summarization. The current mainstream method that deploys…