Two Approaches to Diachronic Normalization of Polish Texts
This addresses the challenge of normalizing historical Polish texts for researchers and linguists, but it is incremental as it compares existing method types without a major breakthrough.
The paper tackled the problem of diachronic normalization of Polish texts by comparing a rule-based method with handcrafted patterns and a neural model based on the text-to-text transfer transformer, finding that the rule-based solution outperformed the neural one on 3 out of 4 dataset variants.
This paper discusses two approaches to the diachronic normalization of Polish texts: a rule-based solution that relies on a set of handcrafted patterns, and a neural normalization model based on the text-to-text transfer transformer architecture. The training and evaluation data prepared for the task are discussed in detail, along with experiments conducted to compare the proposed normalization solutions. A quantitative and qualitative analysis is made. It is shown that at the current stage of inquiry into the problem, the rule-based solution outperforms the neural one on 3 out of 4 variants of the prepared dataset, although in practice both approaches have distinct advantages and disadvantages.