Search

The paper describes a method for finding diachronic spelling variants in a corpus that consists of historical and modern Polish texts. The procedure applies the Levenshtein distance and the similarity measure determined with a Word2vec model. The method was applied for both words and sub-word units. A sample of spelling variants was manually evaluated and compared against an existing morphological analyser for Polish historical texts. The resulting lists of spelling variants and spelling modernisation rules were used in a text modernisation tool and their contribution was evaluated. The paper also presents an analogous method for finding spelling variants that result from erroneous OCR. The obtained lists of OCR variants and rules may serve for the correction of OCR output. [ABSTRACT FROM AUTHOR]

Neural Machine Translation (NMT) has recently achieved promising results for a number of translation pairs. Although the method requires larger volumes of data and more computational power than Statistical Machine Translation (SMT), it is believed to become dominant in near future. In this paper we evaluate SMT and NMT models learned on a domain-specific English-Polish corpus of a moderate size (1,200,000 segments). The experiment shows that both solutions significantly outperform a general-domain online translator. The SMT model achieves a slightly better BLEU score than the NMT model. On the other hand, the process of decoding is noticeably faster in NMT. Human evaluation carried out on a sizeable sample of translations (2,000 pairs) reveals the superiority of the NMT approach, particularly in the aspect of output fluency. [ABSTRACT FROM AUTHOR]