Language Models II: Word Segmentation

"The future is independent of the past, given the present." Orthography encapsulates a set of conventions for a written language, which includes spellings, punctuation, hyphenation, capitalisation, and other features. For example, in English, we begin a sentence with a capital letter and have spaces between words; each word is spelt in a unique way (most of the times), and we use commas to separate clauses and mark the end of a sentence with a period. Reading about the history of English spelling is fascinating. You probably know Geoffrey Chaucer for his collection of short stories, The Canterbury Tales.