Nguyen, Cam-Van Thi
(2019)
A Large Scale Multi-label Text Classification Methodusing Z-Label LDA.
Technical Report.
UET-VNU.
(Submitted)
Abstract
Multi-label Learning (MLL) is a supervised learning model that hasattracted much attention of the research community in recent yearsbecause of its wide variety applicability. In this paper, we built amulti-label classification model using Latent Dirichlet Allocationwith Topic-in-set Knowlegde (z-Label LDA) on the Vietnamesedata domain. z-Label LDA is a variant of LDA which is intended toprovide additional supervised information as a hidden topic into theLDA called "z-label". We also have experimented on the dataset inthe field of Education collected from Vietnamese online newspapers.Parallel, we applied the hidden topic model LDA to generate aprior-knowledge dataset comprising topics and typical keywordsrepresenting each topic. The supervised information also makesthe topic assignment more consistent. With this approach, theeffectiveness of the model has been demonstrated experimentally,this paper has obtained initial positive results.
Actions (login required)
 |
View Item |
