paper-with-me

Papers

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

2024-03-15 · Tomasz Limisiewicz, Terra Blevins, Hila Gonen, Orevaoghene Ahia, Luke Zettlemoyer

A major consideration in multilingual language modeling is how to best represent languages with diverse vocabularies and scripts. Although contemporary text encoding methods cover most of the world's writing systems, they exhibit bias towards the high-resource languages of the Global West. As a result, texts of underrepresented languages tend to be segmented into long sequences of linguistically meaningless units. To address the disparities, we introduce a new paradigm that encodes the same information with segments of consistent size across diverse languages. Our encoding convention (MYTE) is based on morphemes, as their inventories are more balanced across languages than characters, which are used in previous methods. We show that MYTE produces shorter encodings for all 99 analyzed languages, with the most notable improvements for non-European languages and non-Latin scripts. This, in turn, improves multilingual LM performance and diminishes the perplexity gap throughout diverse languages.

📄 PDF Abstract BibTeX arXiv:2403.10691

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Equity with Efficiency: An Empirical Study of Tokenizers for Multilingual Large Language Models

2026-06-13 · Kieron Seven Jun Wei Lee, Muhammad Reza Qorib, Andrew Ivan Soegeng, Hwee Tou Ng arxiv

Multilingual large language models (LLMs) depend on subword tokenization to bridge discrete text and continuous neural representation. State-of-the-art multilingual LLMs often use Byte-level Byte-Pair Encoding (BPE) toke…

Meaningless yet meaningful: Morphology grounded subword-level NMT

2018-06-01 · WS 2018 6 · Tamali Banerjee, Pushpak Bhattacharyya

We explore the use of two independent subsystems Byte Pair Encoding (BPE) and Morfessor as basic units for subword-level neural machine translation (NMT). We show that, for linguistically distant language-pairs Morfessor…

Machine TranslationNMTSegmentationTranslation+1

Morphology-aware Word-Segmentation in Dialectal Arabic Adaptation of Neural Machine Translation

2019-08-01 · WS 2019 8 · Ahmed Tawfik, Mahitab Emam, Khaled Essam, Robert Nabil 외

Parallel corpora available for building machine translation (MT) models for dialectal Arabic (DA) are rather limited. The scarcity of resources has prompted the use of Modern Standard Arabic (MSA) abundant resources to c…

Machine TranslationSegmentationTranslation

BHARATI: Morphology-Aware Tokenizers for Classical Indian Languages with Subword Fertility Analysis

2026-07-25 · Poornima Kumaresan, Pavithra Muruganantham, Lakshmi Rajendran, Santhosh Sivasubramani arxiv

Standard subword tokenization algorithms such as Byte-Pair Encoding (BPE) and SentencePiece are trained predominantly on modern language corpora and produce inefficient segmentations when applied to classical Indian lang…

VerChol -- Grammar-First Tokenization for Agglutinative Languages

2026-03-06 · Prabhu Raja arxiv

Tokenization is the foundational step in all large language model (LLM) pipelines, yet the dominant approach Byte Pair Encoding (BPE) and its variants is inherently script agnostic and optimized for English like morpholo…