Show HN: Tuchu – Automatically highlight the important parts of a document

Re:Show HN: Tuchu – Automatically highlight the important pa... by jhvkjhk on Monday December 28, 2020 @11:24PM (#25566701)

I tested with a 26 pages Chinese pdf and the answer is no, Tuchu only highlighted three English sentences.

This is weird, as Tuchu means highlight in Chinese.

[ Parent | on HN ]

Re:Show HN: Tuchu – Automatically highlight the important pa... by heresjohnny on Tuesday December 29, 2020 @04:29AM (#25568164)

Hi jhvkjhk,

Thanks for your feedback. In theory all languages should be supported since TextRank should be language-agnostic. Having said that, I think that my current sentence similarity strategy (by word overlap) is not a good fit for "symbol rich" languages such as Mandarin.

I am not Chinese (or from Asian descent) myself. Tuchu comes from some rainy Sunday Google translating. ;)

[ Parent | on HN ]