ICNLSP 2024: Native Language Identification Improves Authorship Attribution

Native Language Identification Improves Authorship Attribution
By: Ahmet Yavuz Uluslu, Gerold Schneider, Can Yildizli
University of Zurich
7th International Conference on Natural Language and Speech Processing.
icnlsp.org/202...
Abstract:
This study investigates the integration of native language identification into authorship attribution, a previously unexplored aspect that is particularly important in multilingual contexts. We introduce AA-NLI50, a new dataset containing both native language and authorship information. We propose a zero-shot chain-of-thought approach for native language identification. Our findings demonstrate that our system significantly enhances authorship attribution performance, with results showing a mean accuracy improvement of 9% over baseline methods.