VARD 2: A tool for dealing with spelling variation in historical corpora

Spelling variation causes considerable problems for corpus linguistic techniques such as frequency analysis, concordancing and automatic tagging, with a significant impact being made on recall and the accuracy of results [1]. This paper will focus on Early Modern English, the most recent period of the English language to include a large amount of inconsistent spelling. Although many corpora of Early Modern English have been constructed, including Helsinki, ARCHER [2], the Corpus of Early English Correspondence [3], Corpus of English Dialogues [4] and also many different versions of Shakespeare’s works, little research has been completed to deal with the problem of spelling variation within digitised forms of these texts. With the increasing amount of historical data being digitised through current initiatives, including Early English Books Online 1 , it is imperative that techniques are found to aid the search and retrieval within such datasets.