A5087522507- Natural Language Processing Techniques
- Semantic Web and Ontologies
- Topic Modeling
- Software Engineering Research
Fudan University
2024
Recently, many large language models (LLMs) have been proposed, showing advanced proficiency in code generation. Meanwhile, efforts dedicated to evaluating LLMs on generation benchmarks such as HumanEval. Although being very helpful for comparing different LLMs, existing evaluation focuses a simple scenario (i.e., function-level or statement-level generation), which mainly asks generate one single unit (e.g., function statement) the given natural description. Such generating independent and...
Code translation converts code from one programming language to another while maintaining its original functionality, which is crucial for software migration, system refactoring, and cross-platform development. Traditional rule-based methods rely on manually-written rules, can be time-consuming often result in less readable code. To overcome this, learning-based have been developed, leveraging parallel data train models automated translation. More recently, the advance of Large Language...