用10个固定词元表示数字笔迹，生成与识别效果均优于传统方法。
ScribeTokens: Fixed-Vocabulary Tokenization of Digital Ink
- 将笔迹分解为像素级步进，结合状态词元构建10词元固定词汇表。
- 手写生成任务中词元法错误率仅17.33%，远低于向量法的70.29%。
- 无需预训练即可超越向量，且自监督预训练加速收敛达83倍。
数字笔迹——从笔或触摸输入捕获的坐标流——缺乏统一表示方式。连续向量表示会产生长序列并导致训练不稳定，而现有词元表示需要大词汇表，存在未登录词问题，且在识别任务上表现不如向量。我们提出ScribeTokens，将笔迹运动分解为单位像素步进，并结合两个笔状态词元，构建仅含10个词元的固定基础词汇表，足以表示任意数字笔迹，并支持高效的BPE压缩。在手写文本生成任务中，ScribeTokens显著优于向量（字符错误率17.33% vs. 70.29%），表明词元在生成任务中更高效。在识别任务中，ScribeTokens是唯一在无预训练情况下超越向量的方法。我们进一步引入下一词元预测作为自监督预训练策略，该策略在所有基于词元的模型中持续提升识别性能，并使收敛速度最高加快83倍。经预训练后，ScribeTokens在两个数据集上均取得最优结果：IAM数据集上为8.27% CER，DeepWriting数据集上为9.83% CER。
原文摘要 · Abstract (English)
Digital ink -- the coordinate stream captured from stylus or touch input -- lacks a unified representation. Continuous vector representations produce long sequences and suffer from training instability, while existing token representations require large vocabularies, face out-of-vocabulary issues, and underperform vectors on recognition. We propose ScribeTokens, a tokenization that decomposes pen movement into unit pixel steps. Together with two pen-state tokens, this fixed 10-token base vocabulary suffices to represent any digital ink and enables aggressive BPE compression. On handwritten text generation, ScribeTokens dramatically outperforms vectors (17.33% vs. 70.29% CER), showing tokens are far more effective for generation. On recognition, ScribeTokens is the only token representation to outperform vectors without pretraining. We further introduce next-ink-token prediction as a self-supervised pretraining strategy, which consistently improves recognition across all token-based models and accelerates convergence by up to 83x. With pretraining, ScribeTokens achieves the best recognition results across all representations on both datasets (8.27% CER on IAM, 9.83% on DeepWriting).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。