In recent advances in automatic text recognition (ATR), deep neural networks have demonstrated the ability to implicitly capture language statistics, potentially reducing the need for traditional language models. This study directly addresses whether explicit language models, specifically n-gram models, still contribute to the performance of state-of-the-art deep learning architectures in the field of handwriting recognition. We evaluate two prominent neural network architectures, PyLaia and DAN, with and without the integration of explicit n-gram language models. Our experiments on three datasets - IAM, RIMES, and NorHand v2 - at both line and page level, investigate optimal parameters for n-gram models, including their order, weight, smoothing methods and tokenization level. The results show that incorporating character or subword n-gram models significantly improves the performance of ATR models on all datasets, challenging the notion that deep learning models alone are sufficient for optimal performance. In particular, the combination of DAN with a character language model outperforms current benchmarks, confirming the value of hybrid approaches in modern document analysis systems.

翻译：在自动文本识别（ATR）的最新进展中，深度神经网络已展现出隐式捕捉语言统计信息的能力，这可能降低了对传统语言模型的需求。本研究直接探讨显式语言模型（特指N元语法模型）是否仍能为手写识别领域最先进的深度学习架构的性能做出贡献。我们评估了两种主流神经网络架构PyLaia和DAN，分别在有/无集成显式N元语法语言模型的情况下进行实验。我们在三个数据集（IAM、RIMES和NorHand v2）上，针对行级和页面级任务，研究了N元语法模型的最优参数，包括其阶数、权重、平滑方法和分词级别。结果表明，在字符或子词级别集成N元语法模型显著提升了所有数据集上ATR模型的性能，挑战了“仅凭深度学习模型即可达到最优性能”的观点。尤其值得注意的是，DAN与字符语言模型的组合超越了当前基准，证实了混合方法在现代文档分析系统中的价值。