Traditional authorship verification methods outperform transformers on German video transcripts

A new study published on arXiv explores the effectiveness of Authorship Verification (AV) techniques on transcribed German-language videos. The research found that traditional AV methods, particularly those using character and token n-grams, performed better than modern transformer-based approaches. The best performing traditional methods achieved up to 88% accuracy and 90% AUC on a corpus of 300 videos from 150 speakers, suggesting their continued relevance in the field. AI

IMPACT Highlights the continued relevance of traditional NLP techniques for specific tasks, even as transformer models dominate general AI research.

RANK_REASON Academic paper detailing a new application of existing methods to a novel dataset. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• arXiv
• Authorship Verification
• English
• German
• Hugging Face

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →