Generative ai for software metadata: Overview of the information retrieval in software engineering track at fire 2023

S Majumdar, S Paul, D Paul, A Bandyopadhyay… - arxiv preprint arxiv …, 2023 - arxiv.org
The Information Retrieval in Software Engineering (IRSE) track aims to develop solutions for
automated evaluation of code comments in a machine learning framework based on human …

Automated evaluation of comments to aid software maintenance

S Majumdar, A Bansal, PP Das… - Journal of Software …, 2022 - Wiley Online Library
Approaches to evaluate comments based on whether they increase code comprehensibility
for software maintenance tasks are important, but largely missing. We propose Comment P …

Efficiency of Large Language Models to scale up Ground Truth: Overview of the IRSE Track at Forum for Information Retrieval 2023

S Paul, S Majumdar, A Bandyopadhyay… - Proceedings of the 15th …, 2023 - dl.acm.org
The Software Engineering Information Retrieval (IRSE) track aims to devise solutions for the
automated evaluation of code comments within a machine learning framework, with labels …

SoCCMiner: a source code-comments and comment-context miner

M Sridharan, M Mäntylä, M Claes… - Proceedings of the 19th …, 2022 - dl.acm.org
Numerous tools exist for mining source code and software development process metrics.
However, very few publicly available tools focus on source code comments, a crucial …

Identification of the relevance of comments in codes using bag of words and transformer based models

T Basu - arxiv preprint arxiv:2308.06144, 2023 - arxiv.org
The Forum for Information Retrieval (FIRE) started a shared task this year for classification of
comments of different code segments. This is binary text classification task where the …

A ML-LLM pairing for better code comment classification

H Abi Akl - FIRE (Forum for Information Retrieval Evaluation) 2023, 2023 - inria.hal.science
The" Information Retrieval in Software Engineering (IRSE)" at FIRE 2023 shared task
introduces code comment classification, a challenging task that pairs a code snippet with a …

Enhancing Code Annotation Reliability: Generative AI's Role in Comment Quality Assessment Models

S Killivalavan, D Thenmozhi - arxiv preprint arxiv:2410.22323, 2024 - arxiv.org
This paper explores a novel method for enhancing binary classification models that assess
code comment quality, leveraging Generative Artificial Intelligence to elevate model …

Smart Knowledge Transfer using Google-like Search

S Majumdar, PP Das - arxiv preprint arxiv:2308.06653, 2023 - arxiv.org
To address the issue of rising software maintenance cost due to program comprehension
challenges, we propose SMARTKT (Smart Knowledge Transfer), a search framework, which …

CSDA: A novel attention-based LSTM approach for code search

L Ren, S Shan, K Wang, K Xue - Journal of Physics: Conference …, 2020 - iopscience.iop.org
Previous studies have proposed semantic-based approaches for code search over large-
scale codebases, which has bridged the gap in understanding the semantics between …

A ML-LLM pairing for better code comment classification

HA Akl - arxiv preprint arxiv:2310.10275, 2023 - arxiv.org
The" Information Retrieval in Software Engineering (IRSE)" at FIRE 2023 shared task
introduces code comment classification, a challenging task that pairs a code snippet with a …