ScribeTokens: 数字墨迹的固定词汇分词
ScribeTokens: Fixed-Vocabulary Tokenization of Digital Ink
AI总结:
ScribeTokens通过固定词汇表的分词方法,有效提升了数字墨迹的生成和识别性能,尤其在无需预训练的情况下超越向量表示。
摘要:
数字墨迹——通过触控输入捕获的坐标流——缺乏统一的表示方式。连续向量表示会产生长序列,并且在训练过程中容易不稳定,而现有的分词表示需要大型词汇表,面临词汇外问题,并且在识别任务上表现不如向量。我们提出了ScribeTokens,一种将笔迹运动分解为单位像素步骤的分词方法。结合两个笔状态分词,这种固定10个分词的词汇表足以表示任何数字墨迹,并能够进行激进的BPE压缩。在手写文本生成中,ScribeTokens明显优于向量(17.33% vs. 70.29% CER),表明分词在生成任务中远比向量更有效。在识别方面,ScribeTokens是唯一一种在不预训练的情况下能超越向量的分词表示。我们进一步引入了next-ink-token预测作为自监督预训练策略,这种策略在所有基于分词的模型上都一致地提高了识别性能,并且通过预训练可以加速收敛,最多提高83倍。通过预训练,ScribeTokens在两个数据集上均取得了所有表示中最佳的识别结果(IAM数据集8.27% CER,DeepWriting数据集9.83% CER)。
英文摘要:
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).
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。