Interactive Coding Platform with Code Summarizer

This study presents a Code Summarizer cum Explanation Tool which helps as the student specially those who are beginner in the world of coding to understand other’s solution for a given problem statement. Our approach involves the utilization of this state-of- the-art language model, widely acknowledged for its prowess in handling various text- related tasks such as code generation and summarization. In this study we have use an open-sourced state-of-the art large language model which is used for many downstream text related task such as code generation, code summarisation, etc. and consist of 7 Billion parameters (weights & biases) developed by Technology Innovation Institute (TIIUAE). We fine-tuned the said model on our custom dataset for code explanation task. We have fine-tuned the model for 1 epoch which took approximate 3 hours on 590 steps. As a result we have obtained a brief summary, when given code as a prompt input. By bridging the gap between theoretical understanding and practical application, our Code Summarizer/Explanation Tool can become an useful tool for beginners on their coding journey.

Authors

Institutions

Publication Details

Published
2024-11-29
DOI
https://doi.org/10.1109/idicaiei61867.2024.10842863
Primary Topic
Distributed and Parallel Computing Systems
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Interactive Coding Platform with Code Summarizer

Priyanka Jaiswal, Anushree Dhomne, Sakshi Rawarkar, Sanket Bulkunde et al.
Distributed and Parallel Computing Systems
article

Interactive Coding Platform with Code Summarizer

Priyanka Jaiswal, Anushree Dhomne, Sakshi Rawarkar, Sanket Bulkunde, Sarvesh Lanjewar, Vedant Mundel
article en

Abstract

This study presents a Code Summarizer cum Explanation Tool which helps as the student specially those who are beginner in the world of coding to understand other’s solution for a given problem statement. Our approach involves the utilization of this state-of- the-art language model, widely acknowledged for its prowess in handling various text- related tasks such as code generation and summarization. In this study we have use an open-sourced state-of-the art large language model which is used for many downstream text related task such as code generation, code summarisation, etc. and consist of 7 Billion parameters (weights & biases) developed by Technology Innovation Institute (TIIUAE). We fine-tuned the said model on our custom dataset for code explanation task. We have fine-tuned the model for 1 epoch which took approximate 3 hours on 590 steps. As a result we have obtained a brief summary, when given code as a prompt input. By bridging the gap between theoretical understanding and practical application, our Code Summarizer/Explanation Tool can become an useful tool for beginners on their coding journey.

Yashwantrao Chavan Maharashtra Open University (IN)
Openalex Percentile: Top 70%
Distributed and Parallel Computing Systems
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.