Editing Morpheme (section)

== Morphological analysis ==
In [[natural language processing]] for [[Japanese language|Japanese]], [[Chinese language|Chinese]], and other languages, morphological analysis is the process of segmenting a sentence into a row of morphemes. Morphological analysis is closely related to [[part-of-speech tagging]], but word segmentation is required for those languages because word boundaries are not indicated by blank spaces.<ref>{{Cite book |last=Nakagawa |first=Tetsuji |chapter=Chinese and Japanese word segmentation using word-level and character-level information |date=2004 |title=Proceedings of the 20th international conference on Computational Linguistics - COLING '04 |chapter-url=http://portal.acm.org/citation.cfm?doid=1220355.1220422 |language=en |location=Geneva, Switzerland |publisher=Association for Computational Linguistics |pages=466–es |doi=10.3115/1220355.1220422|s2cid=2988891 |doi-access=free }}</ref>

The purpose of morphological analysis is to determine the minimal units of meaning in a language (morphemes) by comparison of similar forms: such as comparing "She is walking" and "They are walking" with each other, rather than either with something less similar like "You are reading". Those forms can be effectively broken down into parts, and the different morphemes can be distinguished.

Both meaning and form are equally important for the identification of morphemes. An agent morpheme is an affix like ''-er'' that in English transforms a verb into a noun (e.g. ''teach'' → ''teacher''). English also has another morpheme that is identical in pronunciation (and written form) but has an unrelated meaning and function: a comparative morpheme that changes an adjective into another degree of comparison (but remains the same adjective) (e.g. ''small'' → ''smaller''). The opposite can also occur: a pair of morphemes with identical meaning but different forms.<ref name="language files" />