DEFTri: A Few-Shot Label Fused Contextual Representation Learning For Product Defect Triage in e-Commerce
This addresses inefficiencies in time-sensitive defect assignment for e-commerce software development, though it is incremental as it builds on existing BERT methods with domain-specific adaptations.
The paper tackles automated defect triage in e-commerce by proposing DEFTri, a framework using fine-tuned BERT with label-fused text embeddings, which achieved a 15% improvement in F1-score over baselines on a proprietary Walmart dataset.
Defect Triage is a time-sensitive and critical process in a large-scale agile software development lifecycle for e-commerce. Inefficiencies arising from human and process dependencies in this domain have motivated research in automated approaches using machine learning to accurately assign defects to qualified teams. This work proposes a novel framework for automated defect triage (DEFTri) using fine-tuned state-of-the-art pre-trained BERT on labels fused text embeddings to improve contextual representations from human-generated product defects. For our multi-label text classification defect triage task, we also introduce a Walmart proprietary dataset of product defects using weak supervision and adversarial learning, in a few-shot setting.