JacyNumbers

Numbers, Numeral Classifiers and more

Kanji NUmbers

Hindu-Arabic numbers

What we should do is parse numbers and pass them through using SMAF.

ChaSen settings

We set ChaSen to join numbers together:

(連結品詞 ((名詞 数))
          ((記号 アルファベット)))
(COMPOSIT_POS ((名詞 数))
          ((記号 アルファベット)))

Work Around

Until we have a proper preprocessor, we just add all numbers from 0--999, using the script utils/make-num.perl. We could add more as needed.

References

• Bender, Emily M. 2002. http:http://faculty.washington.edu/ebender/papers/jnn.pdf Number Names in Japanese: A Head-Medial Construction in a Head-Final Language. manuscript (comments welcome)