Authors: F Farsi, S Sabouri, K Kashfipour, S Gooran, H Sameti, E Asgari Venue: Preprints.org, 2024
Summary
Data augmentation for Farsi question answering: converts short QA pairs into full, complete answers by syntactic transformation.
Related
Sharif University of Technology — Speech and Language Processing Lab — where this line of Farsi QA work originated. Docalog: Multi-Document Dialogue System Using Transformer-Based Span Retrieval — related document-grounded dialogue work.