Revision as of 15:45, 4 March 2006 edit Jorge Stolfi (talk \| contribs) Autopatrolled, Extended confirmed users, Rollbackers 27,656 edits m moved Word segmentation to Text segmentation: "Word segmentation" suggests the segmentation of words into morphemes, which is not what the article was meant to be about. "Text segmentation" may not be ideal either, but... ← Previous edit		Revision as of 17:18, 24 March 2006 edit undo Scode (talk \| contribs) 42 edits Correct a couple of typos Next edit →
Line 1: '''Written text segmentation''' is the process of diving written text into [[word]]s or other similar meaningful units. The term applies to [[human mind\|mental]] processes used by humans when reading text, and to artificial processes implemented in [[computers]]s, which are the subject [[natural language processing]]. The problem is relatively trivial for written languages that have explicit word boudary markers, such as the word spaces of written [[English language\|English]] ofor the distinctive initial, medial and final letter shapes of [[Arabic language\|Arabic]]. When such clues are not consistently available, the task often requires fairly non-trivial techniques, such as statistical decision-making, large dictionaries, as well as consideration of syntactic and semantic constraints. ==See also==

Text segmentation: Difference between revisions