Challenge: Existing work shows that byte-pair encoding (BPE) tokenization uses a learned merge list to iteratively combine subword units into tokens during inference time.
Approach: They propose to use a standard byte-pair encoding algorithm to pair a learned token vocabulary with a detailed merge list to compress text.
Outcome: The proposed algorithms differ from the encoding process during training and show that the targetted deviation from merge lists exhibits significant degradation in language model performance.

Similar Papers

BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training (2024.emnlp-main)

Copied to clipboard

Challenge: Tokenization is a relatively understudied area, but it can greatly impact model performance and efficiency.
Approach: They propose a modified BPE tokenizer that removes merges that leave intermediate "junk" tokens from the vocabulary.
Outcome: The proposed method improves vocabulary efficiency, eliminates under-trained tokens, and does not compromise text compression.
Finding the Optimal Byte-Pair Encoding Merge Operations for Neural Machine Translation in a Low-Resource Setting (2024.findings-emnlp)

Copied to clipboard

Challenge: Using different byte pair encoder configurations, we can improve neural machine translation performance for low-resource languages.
Approach: They investigate the impact of different Byte Pair Encoding configurations on neural machine translation performance for the Filipino-Cebuano language pair across various text domains.
Outcome: The proposed methods show that smaller BPE configurations yield higher BLEU scores, indicating improved translation quality through finer tokenization granularity . larger BPE setups and the absence of BPE result in lower BLUE scores, suggesting a decline in translation quality due to coarser tokenisation.
Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization (2026.acl-long)

Copied to clipboard

Challenge: Tokenization is the first step of most NLP pipelines.
Approach: They propose a parity-aware byte pair encoder that maximizes the compression gain of the currently worst-compressed language for cross-lingual parity.
Outcome: a new algorithm reduces tokenization inequality by 89% compared to classical BPE . the proposed algorithm is based on a fair-max rule that maximizes the compression gain of the currently worst-compressed language .
Investigating the Effectiveness of BPE: The Power of Shorter Sequences (D19-1)

Copied to clipboard

Challenge: Byte-Pair Encoding (BPE) is an unsupervised sub-word tokenization technique, but its reasons for its effectiveness are not well understood.
Approach: They link BPE to the broader family of dictionary-based compression algorithms and compare it with other members of this family.
Outcome: The proposed method is compared with dictionary-based compression algorithms and improves on a fixed vocabulary size budget.
From Where Words Come: Efficient Regularization of Code Tokenizers Through Source Attribution (2026.acl-long)

Copied to clipboard

Challenge: Currently, subword tokenization is the most common approach for vocabulary building in large models.
Approach: They propose to regularize training and minimize overfitting by using source-attributed BPE . they find that undertrained tokens are prone to producing unused, unusable tokens .
Outcome: The proposed techniques reduce the number of under-trained tokens while maintaining the same inference procedure as with regular BPE.
Byte Pair Encoding is Suboptimal for Language Model Pretraining (2020.findings-emnlp)

Copied to clipboard

Challenge: Subword tokenization is a popular language model that can be used to segment text.
Approach: They analyze differences between byte-pair encoding (BPE) and unigram LM tokenization methods to find subword units that align more closely with morphology.
Outcome: The proposed method recovers subword units that align more closely with morphology and avoids problems stemming from BPE’s greedy construction procedure.
BPE-knockout: Pruning Pre-existing BPE Tokenisers with Backwards-compatible Morphological Semi-supervision (2024.naacl-long)

Copied to clipboard

Challenge: Subword tokenisation is a mainstay in natural language processing (NLP) it allows the representation of an infinite space of text with a finite set of units.
Approach: They propose to use byte-pair encoding to represent an infinite space of text with a finite set of units by removing subwords from the BPE vocabulary without impeding further use of merges that relied on them.
Outcome: The proposed method improves token-based tasks in English, Dutch and German while saving training costs.
Adaptive BPE Tokenization for Enhanced Vocabulary Adaptation in Finetuning Pretrained Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Current vocabulary adaptation approaches append the target domainspecific vocabulary (V DOMAIN) at the end of the PLM vocabulary.
Approach: They propose a vocabulary adaptation scheme that appends a target domain-specific vocabulary (V DOMAIN) at the end of the PLM vocabulary.
Outcome: The proposed approach improves by 3.57% (in terms of accuracy) and 1.87% (royal-L) over various classification and summarization tasks.
Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance (2024.findings-acl)

Copied to clipboard

Challenge: Despite being the cornerstone of BPE, the importance of compression in the tokenization process is still unclear.
Approach: They argue for the theoretical importance of compression in the tokenization process . they also demonstrate the empirical importance of compressing tokenizers for downstream success of pre-trained language models.
Outcome: The proposed method can be viewed as 0-gram language modeling where equal probability is assigned to all tokens.
A Formal Perspective on Byte-Pair Encoding (2023.findings-acl)

Copied to clipboard

Challenge: Byte-Pair Encoding (BPE) is a popular algorithm used for tokenizing data in NLP, but the underlying optimization problem that BPE seeks to solve has not yet been laid down.
Approach: They propose an algorithm which is a 1/sigma*(1-e(-sigma))-approximation of an optimal merge sequence.
Outcome: The proposed algorithm improves the runtime complexity from O(NM) to O(N log M) and the lower bound of the approximation is approx0.37.

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