paper-with-me

Papers

Tokenization and Morphology in Multilingual Language Models: A Comparative Analysis of mT5 and ByT5

2024-10-15 · Thao Anh Dang, Limor Raviv, Lukas Galke

Morphology is a crucial factor for multilingual language modeling as it poses direct challenges for tokenization. Here, we seek to understand how tokenization influences the morphological knowledge encoded in multilingual language models. Specifically, we capture the impact of tokenization by contrasting two multilingual language models: mT5 and ByT5. The two models share the same architecture, training objective, and training data and only differ in their tokenization strategies: subword tokenization vs.\@ character-level tokenization. Probing the morphological knowledge encoded in these models on four tasks and 17 languages, our analyses show that the models learn the morphological systems of some languages better than others and that morphological information is encoded in the middle and late layers. Finally, we show that languages with more irregularities benefit more from having a higher share of the pre-training data.

📄 PDF Abstract BibTeX arXiv:2410.11627

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Gated Linear Unit A Gated Linear Unit, or GLU computes: $$ \mathrm{GLU}(a, b) = a \otimes \sigma(b) $$ It is used in natural language processing architectures, for example the Gated CNN,…
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Inverse Square Root Schedule Inverse Square Root is a learning rate schedule 1 / $\sqrt{\max\left(n, k\right)}$ where $n$ is the current training iteration and $k$ is the number of warm-up steps. This…
Adafactor Adafactor is a stochastic optimization method based on Adam that reduces memory usage while retaining the empirical benefits of…
Multi-Head Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Modelling the Morphology of Verbal Paradigms: A Case Study in the Tokenization of Turkish and Hebrew

2026-02-05 · Giuseppe Samo, Paola Merlo arxiv

We investigate how transformer models represent complex verb paradigms in Turkish and Modern Hebrew, concentrating on how tokenization strategies shape this ability. Using the Blackbird Language Matrices task on natural …

Comparative analysis of subword tokenization approaches for Indian languages

2025-05-22 · Sudhansu Bala Das, Samujjal Choudhury, Tapas Kumar Mishra, Bidyut Kr. Patra

Tokenization is the act of breaking down text into smaller parts, or tokens, that are easier for machines to process. This is a key phase in machine translation (MT) models. Subword tokenization enhances this process by …

Machine TranslationTranslation

Morphemes Without Borders: Evaluating Root-Pattern Morphology in Arabic Tokenizers and LLMs

2026-03-16 · Yara Alakeel, Chatrine Qwaider, Hanan Aldarmaki, Sawsan Alqahtani arxiv

This work investigates how effectively large language models (LLMs) and their tokenization schemes represent and generate Arabic root-pattern morphology, probing whether they capture genuine morphological structure or re…

On the Importance of Tokenization in Arabic Embedding Models

2020-12-01 · COLING (WANLP) 2020 12 · Mohamed Alkaoud, Mairaj Syed

Arabic, like other highly inflected languages, encodes a large amount of information in its morphology and word structure. In this work, we propose two embedding strategies that modify the tokenization phase of tradition…

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…