Main Content


Extract named entity information from MeCab output for Japanese

Since R2019b


entities = textanalytics.ja.mecabToNER(words,info) extracts named entity information given MeCab output in the format returned by the MeCab-ipadic dictionary.

Input Arguments

collapse all

Input tokens, specified as a string vector.

Data Types: string

Information struct with the following fields:

  • Feature – String vector of tokens of the same size as words containing the MeCab output lines in ChaSen format without the split tokens themselves.

  • PartOfSpeech – Numerical code used inside the MeCab-ipadic dictionary for the part-of-speech classification.

Data Types: struct

Output Arguments

collapse all

Extracted entity information, returned as a categorical vector the same size as words.

Version History

Introduced in R2019b