MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual
Language Modeling

MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling

15 March 2024

Tomasz Limisiewicz

Orevaoghene Ahia

Luke Zettlemoyer

Papers citing "MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling"

7 / 7 papers shown

Title
MoCE: Adaptive Mixture of Contextualization Experts for Byte-based Neural Machine Translation Langlin Huang Mengyu Bu Yang Feng 21 0 0 03 Nov 2024
MrT5: Dynamic Token Merging for Efficient Byte-level Language Models Julie Kallini Shikhar Murty Christopher D. Manning Christopher Potts Róbert Csordás 30 2 0 28 Oct 2024
Exact Byte-Level Probabilities from Tokenized Language Models for FIM-Tasks and Model Ensembles Buu Phan Brandon Amos Itai Gat Marton Havasi Matthew Muckley Karen Ullrich 45 1 0 11 Oct 2024
Natural Language Processing RELIES on Linguistics Juri Opitz Shira Wein Nathan Schneider AI4CE 44 7 0 09 May 2024
Morphology Matters: A Multilingual Language Modeling Analysis Hyunji Hayley Park Katherine J. Zhang Coleman Haley K. Steimel Han Liu Lane Schwartz 39 47 0 11 Dec 2020
Improving Multilingual Models with Language-Clustered Vocabularies Hyung Won Chung Dan Garrette Kiat Chuan Tan Jason Riesa VLM 58 65 0 24 Oct 2020
Word Translation Without Parallel Data Alexis Conneau Guillaume Lample MarcÁurelio Ranzato Ludovic Denoyer Hervé Jégou 165 1,630 0 11 Oct 2017