for example, have text consists of lines. each line has own length, indent , other features. goal find poems in text, of clustering methods know reorder lines , build clusters independently of position in text. i've tried use position 1 of features, don't result. cool if hint me dbscan. can me?
supposedly clustering not right tool problem. there segmentation algorithm can adopted problem.
butt better consider optimization problem, , solve such instead of hoping clustering algorithm happens work.
Comments
Post a Comment