# Train One Get One Free: Partially Supervised Neural Network for Bug Report Duplicate Detection and Clustering

## TL;DR

This paper introduces a neural network model that jointly detects duplicate bug reports and clusters them into topics, reducing supervision needs and improving accuracy in bug report management.

## Contribution

A novel partially supervised neural architecture that combines duplicate detection and topic clustering in bug reports, leveraging a joint loss function and attention mechanisms.

## Key findings

- Outperforms state-of-the-art duplicate detection methods.
- Learns meaningful bug report clusters without extra supervision.
- Effective on datasets marked by engineers and non-technical annotators.

## Abstract

Tracking user reported bugs requires considerable engineering effort in going through many repetitive reports and assigning them to the correct teams. This paper proposes a neural architecture that can jointly (1) detect if two bug reports are duplicates, and (2) aggregate them into latent topics. Leveraging the assumption that learning the topic of a bug is a sub-task for detecting duplicates, we design a loss function that can jointly perform both tasks but needs supervision for only duplicate classification, achieving topic clustering in an unsupervised fashion. We use a two-step attention module that uses self-attention for topic clustering and conditional attention for duplicate detection. We study the characteristics of two types of real world datasets that have been marked for duplicate bugs by engineers and by non-technical annotators. The results demonstrate that our model not only can outperform state-of-the-art methods for duplicate classification on both cases, but can also learn meaningful latent clusters without additional supervision.