DeepAI
Log In Sign Up

CodeBLEU: a Method for Automatic Evaluation of Code Synthesis

09/22/2020
by   Shuo Ren, et al.
0

Evaluation metrics play a vital role in the growth of an area as it defines the standard of distinguishing between good and bad models. In the area of code synthesis, the commonly used evaluation metric is BLEU or perfect accuracy, but they are not suitable enough to evaluate codes, because BLEU is originally designed to evaluate the natural language, neglecting important syntactic and semantic features of codes, and perfect accuracy is too strict thus it underestimates different outputs with the same semantic logic. To remedy this, we introduce a new automatic evaluation metric, dubbed CodeBLEU. It absorbs the strength of BLEU in the n-gram match and further injects code syntax via abstract syntax trees (AST) and code semantics via data-flow. We conduct experiments by evaluating the correlation coefficient between CodeBLEU and quality scores assigned by the programmers on three code synthesis tasks, i.e., text-to-code, code translation, and code refinement. Experimental results show that our proposed CodeBLEU can achieve a better correlation with programmer assigned scores compared with BLEU and accuracy.

READ FULL TEXT

page 1

page 2

page 3

page 4

02/14/2022

CodeGen-Test: An Automatic Code Generation Model Integrating Program Test Information

Automatic code generation is to generate the program code according to t...
08/05/2022

Out of the BLEU: how should we assess quality of the Code Generation models?

In recent years, researchers have created and introduced a significant n...
06/12/2019

Does BLEU Score Work for Code Migration?

Statistical machine translation (SMT) is a fast-growing sub-field of com...
04/25/2017

Abstract Syntax Networks for Code Generation and Semantic Parsing

Tasks like code generation and semantic parsing require mapping unstruct...
10/03/2020

Code to Comment "Translation": Data, Metrics, Baselining Evaluation

The relationship of comments to code, and in particular, the task of gen...
04/20/2022

Evaluating Commit Message Generation: To BLEU Or Not To BLEU?

Commit messages play an important role in several software engineering t...
07/12/2021

On the Evaluation of Commit Message Generation Models: An Experimental Study

Commit messages are natural language descriptions of code changes, which...