A segmented topic model based on the two-parameter Poisson-Dirichlet process
-
Altmetric Citations
Du, Lan; Buntine, Wray; Jin, Huidong (Warren)
Description
Documents come naturally with structure: a section contains paragraphs which itself contains sentences; a blog page contains a sequence of comments and links to related blogs. Structure, of course, implies something about shared topics. In this paper we take the simplest form of structure, a document consisting of multiple segments, as the basis for a new form of topic model. To make this computationally feasible, and to allow the form of collapsed Gibbs sampling that has worked well to date...[Show more]
dc.contributor.author | Du, Lan | |
---|---|---|
dc.contributor.author | Buntine, Wray | |
dc.contributor.author | Jin, Huidong (Warren) | |
dc.date.accessioned | 2015-12-07T22:16:56Z | |
dc.identifier.issn | 0885-6125 | |
dc.identifier.uri | http://hdl.handle.net/1885/18292 | |
dc.description.abstract | Documents come naturally with structure: a section contains paragraphs which itself contains sentences; a blog page contains a sequence of comments and links to related blogs. Structure, of course, implies something about shared topics. In this paper we take the simplest form of structure, a document consisting of multiple segments, as the basis for a new form of topic model. To make this computationally feasible, and to allow the form of collapsed Gibbs sampling that has worked well to date with topic models, we use the marginalized posterior of a two-parameter Poisson-Dirichlet process (or Pitman-Yor process) to handle the hierarchical modelling. Experiments using either paragraphs or sentences as segments show the method significantly outperforms standard topic models on either whole document or segment, and previous segmented models, based on the held-out perplexity measure. | |
dc.publisher | Kluwer Academic Publishers | |
dc.source | Machine Learning | |
dc.subject | Keywords: Dirichlet process; Document structure; Gibbs sampling; Latent Dirichlet allocation; New forms; Topic model; Internet; Models Document structure; Latent Dirichlet allocation; Segmented topic model; Two-parameter Poisson-Dirichlet process | |
dc.title | A segmented topic model based on the two-parameter Poisson-Dirichlet process | |
dc.type | Journal article | |
local.description.notes | Imported from ARIES | |
local.identifier.citationvolume | 81 | |
dc.date.issued | 2010 | |
local.identifier.absfor | 080109 - Pattern Recognition and Data Mining | |
local.identifier.ariespublication | u3968803xPUB4 | |
local.type.status | Published Version | |
local.contributor.affiliation | Du, Lan, College of Engineering and Computer Science, ANU | |
local.contributor.affiliation | Buntine, Wray, College of Engineering and Computer Science, ANU | |
local.contributor.affiliation | Jin, Huidong (Warren), College of Engineering and Computer Science, ANU | |
local.description.embargo | 2037-12-31 | |
local.bibliographicCitation.startpage | 5 | |
local.bibliographicCitation.lastpage | 19 | |
local.identifier.doi | 10.1007/s10994-010-5197-4 | |
local.identifier.absseo | 970108 - Expanding Knowledge in the Information and Computing Sciences | |
dc.date.updated | 2016-02-24T10:21:26Z | |
local.identifier.scopusID | 2-s2.0-77955656991 | |
local.identifier.thomsonID | 000280845700002 | |
Collections | ANU Research Publications |
Download
File | Description | Size | Format | Image |
---|---|---|---|---|
01_Du_A_segmented_topic_model_based_2010.pdf | 565.71 kB | Adobe PDF | Request a copy |
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.
Updated: 17 November 2022/ Responsible Officer: University Librarian/ Page Contact: Library Systems & Web Coordinator