Litcius/Paper detail

Probing Toxic Content in Large Pre-Trained Language Models

Nedjma Ousidhoum, Xinran Zhao, Tianqing Fang, Yangqiu Song, Dit‐Yan Yeung

202168 citationsDOIOpen Access PDF

Abstract

Nedjma Ousidhoum, Xinran Zhao, Tianqing Fang, Yangqiu Song, Dit-Yan Yeung. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Topics & Concepts

FangComputational linguisticsComputer scienceNatural language processingVolume (thermodynamics)Joint (building)Content (measure theory)Association (psychology)Artificial intelligenceLinguisticsEngineeringPhilosophyEcologyMathematicsEpistemologyBiologyPhysicsArchitectural engineeringQuantum mechanicsMathematical analysisHate Speech and Cyberbullying DetectionTopic ModelingNatural Language Processing Techniques
Probing Toxic Content in Large Pre-Trained Language Models | Litcius