The Identification of Spelling Variants in English and German Historical Texts: Manual or Automatic?  

Oleh:

Pilz, Thomas ; Ernst-Gerlach, Andrea ; Kempken, Sebastian ; Rayson, Paul ; Archer, Dawn

Jenis: Article from Journal - e-Journal
Dalam koleksi: Literary and Linguistic Computing vol. 23 no. 1 (Apr. 2008), page 65-72.
Fulltext: Vol 23, 1, p 65-72.pdf (91.4KB)

Isi artikel

In this article, we describe the respective approaches we have taken when addressing issues of spelling variation in German and English historical texts. More specifically, we describe an experiment to evaluate automatic techniques for the development of letter replacement heuristics against manually created gold standards of known letter replacements rules. As will become clear, the motivation for the research differs according to the team of researchers: the German researchers are seeking to develop a search engine for historical texts; the English researchers want to improve the results obtained when applying corpus linguistic techniques (developed for modern language) to historical data. However, the respective teams do share a longer term goal of assessing whether it is possible to develop a generic spelling detection tool for Indo-European languages.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali