Nan Duan, Daya Guo, Alexey Svyatkovskiy, Shuai Lu, Seung-Won Hwang, Hojae Han
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Code completion, which aims to predict the following code token(s) according to the code context, can improve the productivity of software development. Recent work has proved that statistical language modeling with transformers can greatly improve the performance in the code completion task via learning from large-scale source code datasets. However, current approaches focus only on code context within the file or project, i.e. internal context. Our distinction is utilizing "external" context, inspired by human behaviors of copying from the related code snippets when writing code. Specifically, we propose a retrieval-augmented code completion framework, leveraging both lexical copying and referring to code with similar semantics by retrieval. We adopt a stagewise training approach that combines a source code retriever and an auto-regressive language model for programming language. We evaluate our approach in the code completion task in Python and Java programming languages, achieving a state-of-the-art performance on CodeXGLUE benchmark.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.07722")
get_code_for_paper("2203.07722")
have("2203.07722")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2203.07722.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2203.07722)
Connect an agent — have() is free.