Nonparametric Bayesian topic modelling with the hierarchical Pitman-Yor processes
详细信息 查看全文
- 作者：Kar Wai Lima ; b ; karwai.lim@anu.edu.au" class="auth_mail" title="E-mail the corresponding author ; Wray Buntinec ; wray.buntine@monash.edu" class="auth_mail" title="E-mail the corresponding author ; Changyou Chend ; cchangyou@gmail.com" class="auth_mail" title="E-mail the corresponding author ; Lan Duc ; lan.du@monash.edu" class="auth_mail" title="E-mail the corresponding author
- 关键词：Bayesian nonparametric methods ; Markov chain Monte Carlo ; Topic models ; Hierarchical Pitman&ndash ; Yor processes
- 刊名：International Journal of Approximate Reasoning
- 出版年：2016
- 出版时间：November 2016
- 年：2016
- 卷：78
- 期：Complete
- 页码：172-191
- 全文大小：688 K
文摘
- •
Pitman–Yor processes can be stacked hierarchically to form Bayesian models.
- •
A general modelling framework using hierarchical Pitman–Yor processes is proposed.
- •
Efficient inference algorithm is made possible by modularising the hierarchy.
- •
This framework is applied to Twitter for text and network modelling.