Supervised HDP Using Prior Knowledge
نویسندگان
چکیده
End users can find topic model results difficult to interpret and evaluate. To address user needs, we present a semi-supervised hierarchical Dirichlet process for topic modeling that incorporates user-defined prior knowledge. Applied to a large electronic dataset, the generated topics are more fine-grained, more distinct, and align better with users’ assignments of topics to documents.
منابع مشابه
Wised Semi-Supervised Cluster Ensemble Selection: A New Framework for Selecting and Combing Multiple Partitions Based on Prior knowledge
The Wisdom of Crowds, an innovative theory described in social science, claims that the aggregate decisions made by a group will often be better than those of its individual members if the four fundamental criteria of this theory are satisfied. This theory used for in clustering problems. Previous researches showed that this theory can significantly increase the stability and performance of...
متن کاملExtracting Prior Knowledge from Data Distribution to Migrate from Blind to Semi-Supervised Clustering
Although many studies have been conducted to improve the clustering efficiency, most of the state-of-art schemes suffer from the lack of robustness and stability. This paper is aimed at proposing an efficient approach to elicit prior knowledge in terms of must-link and cannot-link from the estimated distribution of raw data in order to convert a blind clustering problem into a semi-supervised o...
متن کاملWised Semi-Supervised Cluster Ensemble Selection: A New Framework for Selecting and Combing Multiple Partitions Based on Prior knowledge
The Wisdom of Crowds, an innovative theory described in social science, claims that the aggregate decisions made by a group will often be better than those of its individual members if the four fundamental criteria of this theory are satisfied. This theory used for in clustering problems. Previous researches showed that this theory can significantly increase the stability and performance of...
متن کامل10708 Probabilistic Graphical Model Project
Topic Models such as PLSI[7] and LDA[1] have been widely used in text analysis communities as well as other fields such as computer vision. Since the original idea of LDA was proposed, there has been a great deal of extension work such as: supervised Topic Models[2], where a label node was introduced to the model; Hierarchical Dirichlet Processes[7], which solved the nuisance that the number of...
متن کاملMarkers of Vascular Dysfunction After Hypertensive Disorders of Pregnancy: A Systematic Review and Meta-Analysis.
Women with prior hypertensive disorders of pregnancy (HDP) are at twice the risk of cardiovascular disease compared with women with prior normotensive pregnancy, possibly because of sustained vascular dysfunction after delivery. The aim of this systematic review and meta-analysis is to summarize evidence of vascular dysfunction at least 3 months after HDP. Articles in all languages were retriev...
متن کامل