Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization.
Negar Foroutan, Clara Meister, Debjit Paul, Joel Niklaus, Sina Ahmadi, Antoine Bosselut, Rico Sennrich
Browse the full ACL paper archive.
Negar Foroutan, Clara Meister, Debjit Paul, Joel Niklaus, Sina Ahmadi, Antoine Bosselut, Rico Sennrich
Browse the full ACL paper archive.