Northwestern University Information Technology
MorphAdorner Northwestern
Spelling Standardizer

Efforts to adorn English texts covering a period of over four hundred years must deal with the fact that the English language has changed significantly even since the start of the early modern period around 1470 A.D. The great vowel sound shift was only about half complete at this time. Spelling was not at all standardized. Early printed texts reflect the differences in pronunciation. In 1475 William Caxton published (in Bruges) the first book printed in English, Recuyell of the Historyes of Troye. That short title reveals the orthographic variety that existed in early modern English. Spelling was largely standardized by around 1650, at least in print, and was almost entirely standardized by the late eighteenth century. Some regional spelling differences still exist today, but these are relatively minor compared to earlier centuries.

Texts from the seventeenth century and earlier times use conventions that differ from contemporary standards in the use of "u" and "v" and "y" and capitalization, among others. Often the same words is spelled differently even within the same work. By the eighteenth-century texts employ much more modern orthographic standards, except for capitalization.

MorphAdorner uses rules, word lists, and extended search techniques such as spelling correction methods and other heuristics to map variant spellings to their standard (usually modern) form. For obsolete words no longer in use, a representative standard form is chosen which is usually the Oxford English Dictionary headword form. Presently MorphAdorner knows a couple of hundred thousand variant spellings. Using this list, MorphAdorner can automatically determine the correct standard form for previously unseen spellings in many cases.

Sometimes a new spelling is just too different from any of the ones MorphAdorner already knows. Using the extended search facilities on such a spelling may result in a "standard spelling" which veers far from the correct form. As time goes one we hope to reduce the occurrence of such errors.

Orthographic standardization improves the quality of part-of-speech tagging, name recognition, and text searching. However, standardization by itself isn't sufficient to fix some other problems. These include the lack of the apostrophe to mark the possessive case and the inconsistent practices of capitalization as markers of proper nouns.

In English before 1700 the apostrophe never indicates the genitive, and "her mother's daughter" is written "her mothers daughter". An even more problematic example is "her majesty's daughter" which appears in early texts as "her majesties daughter." The use of the apostrophe as a genetive marker gained ground during the eighteenth century, and has been used as it is today since the early nineteenth century.

In the eighteenth century, the apostrophe is sometimes used as a plural marker in certain character combinations. Thus "canoe's" is much more likely to be a plural than a possessive form.

The modern practice of restricting capitalization to names, namelike entities, and certain emphatic uses is about two centuries old. In earlier English nouns are freely capitalized, and capitalization is not a reliable way of picking out proper nouns. However, proper nouns have usually been capitalized in all forms of written English since about 1550. Before that names can appear in lower case.

In poetry the first word of each line is often capitalized even when that word does not start a sentence. For purposes of part-of-speech tagging, a simple workaround is to use the lower case form of a word that does not start a sentence, except if the word appears in a list of known proper names.

You can read a more detailed description of the spelling standardization process.

You can try MorphAdorner's spelling standardizer online.

Announcements and News
Download MorphAdorner
Helpful References
Tech Talk