Sentence Segmentation The problem of deciding where the sentences begin and end. Challenges Involved While ‘!’, ‘?’ are quite unambiguous Period “.” is quite ambiguous and can be used additionally for ) Abbreviations (Dr., Mr., m.p.h.) ) Numbers (2.4%, 4.3) Approach: build a binary classifier For each “.” Decides End Of Sentence/Not End Of Sentence Classifiers can be: hand-written rules, regular expressions, or machine learning