LEAP: Efficient and Automated Test Method for NLP Software

The widespread adoption of DNNs in NLP software has highlighted the need for robustness. Researchers proposed various automatic testing techniques for adversarial test cases. However, existing methods suffer from two limitations: weak error-discovering capabilities, with success rates ranging from 0...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE/ACM International Conference on Automated Software Engineering : [proceedings] S. 1136 - 1148
Hauptverfasser:	Xiao, Mingxuan, Xiao, Yan, Dong, Hai, Ji, Shunhui, Zhang, Pengcheng
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 11.09.2023
Schlagworte:	Adaptation models NLP Software Testing Particle Swarm Optimization Perturbation methods Robustness Scalability Sociology Software algorithms Statistics
ISSN:	2643-1572
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!