Modernizing historical documents: A user Study

Abstract

Accessibility to historical documents is mostly limited to scholars. This is due to the language barrier inherent in human language and the linguistic properties of these documents. Given a historical document, modernization aims to generate a new version of it, written in the modern version of the document's language. Its goal is to tackle the language barrier, decreasing the comprehension difficulty and making historical documents accessible to a broader audience. In this work, we proposed a new neural machine translation approach that profits from modern documents to enrich its systems. We tested this approach with both automatic and human evaluation, and conducted a user study. Results showed that modernization is successfully reaching its goal, although it still has room for improvement.

From Plenipotentiary to Puddingless: Users and Uses of New Words in Early English Letters

“…This may be partly explained by the composition of the sample: in terms of the relationship between the sender and recipient, the largest category is letters between close friends (31%), the proportion of which in the 17th-century sample is c. 21%. (7) Your invocation has mounted me, Merry Andrew-like, upon stilts. -I ape you, as monkeys ape men by walking upon two.…”

“…Normalization is a very common practice embraced in the NLP research when dealing with historical or otherwise non-standard language [7,3,29,9,43]. The benefit of normalization is that it makes non-standard orthography standard and thus enables the use of NLP tools and resources designed for modern normative data.…”

“…Within the classes, the words are again widely dispersed, but the most frequent categories are 'the mind » emotion' and 'society » leisure' at 3 types each. This paints a picture of letters written more for the purposes of keeping in touch and building friendships than for exchanging information, as in example (7). This may be partly explained by the composition of the sample: in terms of the relationship between the sender and recipient, the largest category is letters between close friends (31%), the proportion of which in the 17th-century sample is c. 21%.…”

From Plenipotentiary to Puddingless: Users and Uses of New Words in Early English Letters

“…Normalization is a very common practice embraced in the NLP research when deal ing with historical or otherwise nonstandard language [7,3,29,9,43]. The benefit of nor malization is that it makes nonstandard orthography standard and thus enables the use of NLP tools and resources designed for modern normative data.…”

“…Within the classes, the words are again widely dis persed, but the most frequent categories are 'the mind » emotion' and 'society » leisure' at 3 types each. This paints a picture of letters written more for the purposes of keeping in touch and building friendships than for exchanging information, as in example (7). This may be partly explained by the composition of the sample: in terms of the rela tionship between the sender and recipient, the largest category is letters between close friends (31%), the proportion of which in the 17thcentury sample is c. 21%.…”