Information Retrieval in Software Engineering

(IRSE)

@ FIRE 2023

15th-18th December, 2023

Task Descriptions

Task1: Generative AI based Software Metadata Classification

A binary code comment quality classification model needs to be augmented with generated code and comment pairs that can improve the accuracy of the model.

Input: a) 9048 pairs of code and comments written in C, labeled as either Useful or Not Useful.

b) Code and Comment Pairs, written in C with generated labels of useful / not useful using any Large Language Model Architecture

Output: Classification model with and without the new set of code comment pairs and generated labels

Task2: Translation of Programming Language to Natural Language

Code summaries (intents) are to be generated by training over 40,000 code and intent pairs written in Python.

 Input: Code Snippet 

Output: Code Intent or Summary