When I try to segment a sentence "〜refrain〜 The songs were inspired by "EVANGELION"", I will get the output "^|^|銆淾|^|refrain|^|^|銆淾|^|The|songs|were|inspired|by|&|quot|;|EVANGELION|" (| stands for the border of words)
If I delete the last word "EVANGELION", I will get the correct output "〜|refrain|〜| |The| |songs| |were| |inspired| |by| |&|quot|;|"
I know this program is mainly used for Chinese word segmentation, but I still wonder what causes this problem? It is quite interesting, isn't it?
When I try to segment a sentence "〜refrain〜 The songs were inspired by "EVANGELION"", I will get the output "^|^|銆淾|^|refrain|^|^|銆淾|^|The|songs|were|inspired|by|&|quot|;|EVANGELION|" (| stands for the border of words)
If I delete the last word "EVANGELION", I will get the correct output "〜|refrain|〜| |The| |songs| |were| |inspired| |by| |&|quot|;|"
I know this program is mainly used for Chinese word segmentation, but I still wonder what causes this problem? It is quite interesting, isn't it?