Refining GPT-3 Embeddings with a Siamese Structure for Technical Post Duplicate Detection

1 code implementation • 22 Dec 2023 • Xingfang Wu, Heng Li, Nobukazu Yoshioka, Hironori Washizaki, Foutse khomh

When applied to the dataset we constructed with a recent Stack Overflow dump, our approach attains a Top-1, Top-5, and Top-30 accuracy of 23. 1%, 43. 9%, and 68. 9%, respectively.

Machine Learning Application Development: Practitioners' Insights

no code implementations • 31 Dec 2021 • Md Saidur Rahman, Foutse khomh, Alaleh Hamidi, Jinghui Cheng, Giuliano Antoniol, Hironori Washizaki

In this paper, we report about a survey that aimed to understand the challenges and best practices of ML application development.

BIG-bench Machine Learning

Preliminary Systematic Literature Review of Machine Learning System Development Process

no code implementations • 12 Oct 2019 • Yasuhiro Watanabe, Hironori Washizaki, Kazunori Sakamoto, Daisuke Saito, Kiyoshi Honda, Naohiko Tsuda, Yoshiaki Fukazawa, Nobukazu Yoshioka

Previous machine learning (ML) system development research suggests that emerging software quality attributes are a concern due to the probabilistic behavior of ML systems.

BIG-bench Machine Learning

Studying Software Engineering Patterns for Designing Machine Learning Systems

no code implementations • 10 Oct 2019 • Hironori Washizaki, Hiromu Uchida, Foutse khomh, Yann-Gael Gueheneuc

Machine-learning (ML) techniques have become popular in the recent years.

BIG-bench Machine Learning