BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training

• URL: http://arxiv.org/abs/2409.04599v1
• Date: Fri, 6 Sep 2024 20:12:34 GMT
• Title: BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training
• Authors: Pavel Chizhov, Catherine Arnett, Elizaveta Korotkova, Ivan P. Yamshchikov,
• Abstract summary: Picky BPE is a modified BPE algorithm that carries out vocabulary refinement during tokenizer training. Our method improves vocabulary efficiency, eliminates under-trained tokens, and does not compromise text compression.
• Score: 8.012203293561196
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language models can largely benefit from efficient tokenization. However, they still mostly utilize the classical BPE algorithm, a simple and reliable method. This has been shown to cause such issues as under-trained tokens and sub-optimal compression that may affect the downstream performance. We introduce Picky BPE, a modified BPE algorithm that carries out vocabulary refinement during tokenizer training. Our method improves vocabulary efficiency, eliminates under-trained tokens, and does not compromise text compression. Our experiments show that our method does not reduce the downstream performance, and in several cases improves it.

Related papers

• Theoretical Analysis of Byte-Pair Encoding [0.8655526882770742]
  Byte-Pair (BPE) is a widely used method for subword tokenization. We show that BPE approximates the compression utility of the optimal pair encoding to a worst-case factor.
  arXiv  Detail & Related papers  (2024-11-13T15:04:02Z)
• Adaptive BPE Tokenization for Enhanced Vocabulary Adaptation in Finetuning Pretrained Language Models [26.442558912559658]
  We show a fundamental limitation in vocabulary adaptation approaches that use Byte-Pair. (BPE) tokenization scheme for fine-tuning pretrained language models (PLMs) to expert domains. We propose AdaptBPE where the BPE tokenization phase is modified to first perform the longest string matching on the added (target) vocabulary before tokenizing at the character level.
  arXiv  Detail & Related papers  (2024-10-04T09:24:55Z)
• Batching BPE Tokenization Merges [55.2480439325792]
  BatchBPE is an open-source pure Python implementation of the Byte Pair algorithm. It is used to train a high quality tokenizer on a basic laptop.
  arXiv  Detail & Related papers  (2024-08-05T09:37:21Z)
• Scaffold-BPE: Enhancing Byte Pair Encoding for Large Language Models with Simple and Effective Scaffold Token Removal [58.29382184006158]
  We propose Scaffold-BPE, which incorporates a dynamic scaffold token removal mechanism by parameter-free, computation-light, and easy-to-implement modifications to the original BPE method. On extensive experiments across language modeling and even machine translation, Scaffold-BPE consistently outperforms the original BPE.
  arXiv  Detail & Related papers  (2024-04-27T07:12:07Z)
• Training LLMs over Neurally Compressed Text [55.11828645767342]
  This paper explores the idea of training large language models (LLMs) over highly compressed text. We propose Equal-Info Windows, a novel compression technique whereby text is segmented into blocks that each compress to the same bit length. We demonstrate effective learning over neurally compressed text that improves with scale, and outperforms byte-level baselines by a wide margin on perplexity and inference speed benchmarks.
  arXiv  Detail & Related papers  (2024-04-04T17:48:28Z)
• An Analysis of BPE Vocabulary Trimming in Neural Machine Translation [56.383793805299234]
  vocabulary trimming is a postprocessing step that replaces rare subwords with their component subwords. We show that vocabulary trimming fails to improve performance and is even prone to incurring heavy degradation.
  arXiv  Detail & Related papers  (2024-03-30T15:29:49Z)
• Tokenization Is More Than Compression [14.939912120571728]
  Existing tokenization approaches like Byte-Pair. (BPE) originate from the field of data compression. We introduce PathPiece, a new tokenizer that segments a document's text into the minimum number of tokens for a given vocabulary.
  arXiv  Detail & Related papers  (2024-02-28T14:52:15Z)
• SelfSeg: A Self-supervised Sub-word Segmentation Method for Neural Machine Translation [51.881877192924414]
  Sub-word segmentation is an essential pre-processing step for Neural Machine Translation (NMT) This paper introduces SelfSeg, a self-supervised neural sub-word segmentation method. SelfSeg is much faster to train/decode and requires only monolingual dictionaries instead of parallel corpora.
  arXiv  Detail & Related papers  (2023-07-31T04:38:47Z)
• Byte Pair Encoding is Suboptimal for Language Model Pretraining [49.30780227162387]
  We analyze differences between unigram LM tokenization and byte-pair encoding (BPE) We find that the unigram LM tokenization method matches or outperforms BPE across downstream tasks and two languages. We hope that developers of future pretrained LMs will consider adopting the unigram LM method over the more prevalent BPE.
  arXiv  Detail & Related papers  (2020-04-07T21:21:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.