用于数值规范化的位置描述
Positional Description for Numerical Normalization
AI总结：
提出位置描述方案（PDS），通过保留架构的预处理简化数字规范化，缓解神经模型文本规范化错误，显著提升算术准确率并适用于生产级语音处理。
摘要：
我们提出了一种专为数字序列定制的位置描述方案（PDS），整合了每个数字的占位符值信息。鉴于子词分词算法的结构局限性，语言模型在处理数值任务时面临关键的文本规范化（TN）挑战。我们的方案通过简单的预处理解决此挑战，在保留模型架构的同时显著简化了数字规范化，使问题变得可处理。这简化了任务，并促进了能够从较小数据集中学习的更紧凑的生产级模型。此外，我们的研究表明，PDS增强了语言模型的算术处理能力，在复杂算术任务上实现了23%至51%的相对准确率提升。我们证明PDS有效缓解了神经模型中致命的数值规范化错误，仅需少量训练数据，而无需基于规则的有限状态转换器（FST）。我们证明PDS对文本转语音和语音识别文本处理都至关重要，能够在生产约束下实现有效的TN。
英文摘要：
We present a Positional Description Scheme (PDS) tailored for digit sequences, integrating placeholder value information for each digit. Given the structural limitations of subword tokenization algorithms, language models encounter critical Text Normalization (TN) challenges when handling numerical tasks. Our schema addresses this challenge through straightforward pre-processing, preserving the model architecture while significantly simplifying number normalization, rendering the problem tractable. This simplifies the task and facilitates more compact production-ready models capable of learning from smaller datasets. Furthermore, our investigations reveal that PDS enhances the arithmetic processing capabilities of language models, resulting in a relative accuracy improvement of 23% to 51% on complex arithmetic tasks. We demonstrate that PDS effectively mitigates fatal numerical normalization errors in neural models, requiring only a modest amount of training data without rule-based Finite State Transducers (FST). We demonstrate that PDS is essential for both the Text-To-Speech and Speech Recognition text processing, enabling effective TN under production constraints.
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。
