42 lines
1.2 KiB
Plaintext
42 lines
1.2 KiB
Plaintext
|
; List of features
|
||
|
|
; f[0]: pos1
|
||
|
|
; f[1]: pos2
|
||
|
|
; f[2]: pos3
|
||
|
|
; f[3]: pos4
|
||
|
|
; f[4]: pinyin pronunciation
|
||
|
|
; f[5]: traditional Chinese character form
|
||
|
|
; f[6]: simplified Chinese character form
|
||
|
|
; f[7]: definition
|
||
|
|
|
||
|
|
cost-factor = 700
|
||
|
|
bos-feature = BOS/EOS,*,*,*,*,*,*,*,*,*,*,*,*,*,*,*,*
|
||
|
|
|
||
|
|
; If the analysis target is a known word, eval-size specifies criteria for correct answers.
|
||
|
|
; Unlike Japanese, Chinese has no conjugation.
|
||
|
|
; Therefore, four elements that are pos 1, 2, 3, 4 are evaluated. Other elements, such as pronunciation information, are ignored.
|
||
|
|
eval-size = 4
|
||
|
|
unk-eval-size = 4
|
||
|
|
config-charset = utf8
|
||
|
|
|
||
|
|
output-format-type = cedict
|
||
|
|
|
||
|
|
node-format-cedict = %m\t%f[0],%f[1],%f[2],%f[3],%f[4],%f[5],%f[6],%f[7]\n
|
||
|
|
unk-format-cedict = %m\t%f[0],%f[1],%f[2],%f[3],%f[4],%f[5]\n
|
||
|
|
bos-format-cedict =
|
||
|
|
eos-format-cedict = EOS\n
|
||
|
|
|
||
|
|
node-format-traditional = %f[5]
|
||
|
|
unk-format-traditional = %f[5]
|
||
|
|
bos-format-traditional =
|
||
|
|
eos-format-traditional = \n
|
||
|
|
|
||
|
|
node-format-simplified = %f[6]
|
||
|
|
unk-format-simplified = %f[6]
|
||
|
|
bos-format-simplified =
|
||
|
|
eos-format-simplified = \n
|
||
|
|
|
||
|
|
node-format-gdmandarin = <a href="bword:%f[5]">%f[5]</a>
|
||
|
|
unk-format-gdmandarin = <a href="bword:%f[5]">%f[5]</a>
|
||
|
|
bos-format-gdmandarin =
|
||
|
|
eos-format-gdmandarin = \n
|