Automatic extraction of differences between spoken and written languages, and automatic translation from the written to the spoken language

We extracted the di erences between spoken language and written language from a spoken-language corpus and a writtenlanguage corpus by using the UNIX command \di " and examined the di erences to determine the construction of the grammars of the two corpora. We also transformed written-language sentences into spoken-language sentences by using rules based on the extracted di erences.