Challenge: Tokenization is a fundamental task in natural language processing that forms the first step of many pipelines.
Approach: They propose to use a standard tokenizer trained without MWE-awareness as a baseline and a character-level SRN+CRF model to train token-level models.
Outcome: The proposed tokenizers are based on a character-level and token-level sequence labeling problem and are consistent with the proposed pipelines.

Similar Papers

Multilingual Word Segmentation: Training Many Language-Specific Tokenizers Smoothly Thanks to the Universal Dependencies Corpus (L18-1)

Copied to clipboard

Challenge: Towards language scalability, major progress has been achieved in multilingual language technology in recent years.
Approach: They propose a tokenizer that can be trained from any Universal Dependencies corpus dataset . they argue that tokenization should be seen as a supervised task and scalability requires a software engineering process across languages.
Outcome: The proposed tokenizer can be trained from any dataset in the corpus UD2 . the proposed software tool relies on elephant to perform the training .
Stop Taking Tokenizers for Granted: They Are Core Design Decisions in Large Language Models (2026.eacl-long)

Copied to clipboard

Challenge: Subword tokenization approaches misalign with linguistic structure and waste capacity across languages and domains.
Approach: They argue for a context-aware framework that integrates tokenizer and model co-design . they argue that tokenization should be treated as a core design problem, not an afterthought .
Outcome: The proposed framework integrates tokenizer and model co-design, guided by linguistic, domain, and deployment considerations.
Where are we Still Split on Tokenization? (2024.findings-eacl)

Copied to clipboard

Challenge: Identifying tokens is a crucial first step for many tasks in Natural Language Processing (NLP) gold tokenization is often assumed, but some work on token-level tasks is more challenging.
Approach: They propose an efficient method for tokenization with subword-based language models and evaluate it on 122 languages in 20 scripts.
Outcome: The proposed method performs on par with the state-of-the-art on 122 languages in 20 scripts.
What is the best recipe for character-level encoder-only modelling? (2023.acl-long)

Copied to clipboard

Challenge: aims to benchmark recent progress in language understanding models that output contextualised representations at the character level.
Approach: They aim to find the best way to build and train character-level BERT-like models by comparing architectural innovations with pretraining objectives.
Outcome: The proposed model outperforms a token-based model on a set of evaluation tasks with a fixed training procedure.
A Multi-dimensional Evaluation of Tokenizer-free Multilingual Pretrained Models (2023.findings-eacl)

Copied to clipboard

Challenge: Recent work on tokenizer-free models shows promising results in cross-lingual transfer . previous work focused on reporting accuracy on a limited set of tasks and data settings .
Approach: They compare tokenizer-free and subword-based models using various dimensions . they find subword models are still the most practical choice in many settings .
Outcome: The proposed model improves cross-lingual transfer and reduces engineering overhead.
Multilingual Tokenization through the Lens of Indian Languages: Challenges and Insights (2026.findings-acl)

Copied to clipboard

Challenge: Existing tokenizers are often skewed towards high-resource languages limiting their effectiveness for linguistically diverse and morphologically rich languages.
Approach: They evaluate multilingual tokenization across 17 Indic languages spanning 11 scripts and two language families.
Outcome: The proposed method improves tokenization quality and vocabulary size in 17 languages . poor tokenization can lead to increase in sequence lengths, fragment meaningful units, weaken model's ability to capture linguistic structure and semantics.
Beyond Text Compression: Evaluating Tokenizers Across Scales (2025.acl-long)

Copied to clipboard

Challenge: Language models rely on tokenizers to convert text into machine-interpretable tokens, which shape the statistical patterns that language models learn to estimate.
Approach: They propose to use Zipf's law to measure tokenizer performance by combining several metrics to capture multiple aspects of tokenizer behavior.
Outcome: The proposed metrics correlate more strongly with downstream performance than text compression when modeling unseen languages.
Canine: Pre-training an Efficient Tokenization-Free Encoder for Language Representation (2022.tacl-1)

Copied to clipboard

Challenge: End-to-end neural models have replaced the traditional pipeline and require an explicit tokenization step.
Approach: They propose a neural encoder that operates directly on character sequences without explicit tokenization or vocabulary and a pre-training strategy that optionally uses subwords as a soft inductive bias.
Outcome: The proposed model outperforms a comparable mBert model on a multilingual benchmark by 5.7 F1 on the TyDi QA benchmark.
Phonemes to the Rescue: Multilingual Tokenization Based on International Phonetic Alphabet (2026.acl-long)

Copied to clipboard

Challenge: Widely-used subword tokenization approaches favor high-resource languages and tokenizer-free methods yield longer sequences for scripts with a higher bytes-per-character ratio.
Approach: They propose to use the International Phonetic Alphabet (IPA) as a language-agnostic input representation for multilingual tokenizers.
Outcome: The proposed model improves tokenization quality and generalizes more effectively to unseen languages and scripts.
How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models (2021.acl-long)

Copied to clipboard

Challenge: Using pretraining data, we find that a designated monolingual tokenizer plays an equally important role in the downstream performance of the model.
Approach: They propose to compare pretrained multilingual models with their monolingual counterparts on a set of five diverse monolingual downstream tasks.
Outcome: The proposed models offer previously unmatched performance in all NLP tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations