Integrating Document Clustering and Topic Modeling. Xie, P. & Xing, E., P. Paper Website abstract bibtex Document clustering and topic modeling are two closely related tasks which can mutu-ally benefit each other. Topic modeling can project documents into a topic space which facilitates effective document cluster-ing. Cluster labels discovered by document clustering can be incorporated into topic models to extract local topics specific to each cluster and global topics shared by all clus-ters. In this paper, we propose a multi-grain clustering topic model (MGCTM) which inte-grates document clustering and topic model-ing into a unified framework and jointly per-forms the two tasks to achieve the overall best performance. Our model tightly couples two components: a mixture component used for discovering latent groups in document col-lection and a topic model component used for mining multi-grain topics including local topics specific to each cluster and global top-ics shared across clusters. We employ varia-tional inference to approximate the posterior of hidden variables and learn model param-eters. Experiments on two datasets demon-strate the effectiveness of our model.
@article{
title = {Integrating Document Clustering and Topic Modeling},
type = {article},
websites = {https://arxiv.org/pdf/1309.6874.pdf},
id = {7ebfb27e-4d00-3ec3-9102-961036d27501},
created = {2018-02-05T18:53:21.704Z},
accessed = {2018-02-05},
file_attached = {true},
profile_id = {371589bb-c770-37ff-8193-93c6f25ffeb1},
group_id = {f982cd63-7ceb-3aa2-ac7e-a953963d6716},
last_modified = {2018-02-05T18:53:25.053Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {false},
hidden = {false},
private_publication = {false},
abstract = {Document clustering and topic modeling are two closely related tasks which can mutu-ally benefit each other. Topic modeling can project documents into a topic space which facilitates effective document cluster-ing. Cluster labels discovered by document clustering can be incorporated into topic models to extract local topics specific to each cluster and global topics shared by all clus-ters. In this paper, we propose a multi-grain clustering topic model (MGCTM) which inte-grates document clustering and topic model-ing into a unified framework and jointly per-forms the two tasks to achieve the overall best performance. Our model tightly couples two components: a mixture component used for discovering latent groups in document col-lection and a topic model component used for mining multi-grain topics including local topics specific to each cluster and global top-ics shared across clusters. We employ varia-tional inference to approximate the posterior of hidden variables and learn model param-eters. Experiments on two datasets demon-strate the effectiveness of our model.},
bibtype = {article},
author = {Xie, Pengtao and Xing, Eric P}
}
Downloads: 0
{"_id":"464rwijY9Amjw77jb","bibbaseid":"xie-xing-integratingdocumentclusteringandtopicmodeling","downloads":0,"creationDate":"2018-02-07T16:22:57.329Z","title":"Integrating Document Clustering and Topic Modeling","author_short":["Xie, P.","Xing, E., P."],"year":null,"bibtype":"article","biburl":null,"bibdata":{"title":"Integrating Document Clustering and Topic Modeling","type":"article","websites":"https://arxiv.org/pdf/1309.6874.pdf","id":"7ebfb27e-4d00-3ec3-9102-961036d27501","created":"2018-02-05T18:53:21.704Z","accessed":"2018-02-05","file_attached":"true","profile_id":"371589bb-c770-37ff-8193-93c6f25ffeb1","group_id":"f982cd63-7ceb-3aa2-ac7e-a953963d6716","last_modified":"2018-02-05T18:53:25.053Z","read":false,"starred":false,"authored":false,"confirmed":false,"hidden":false,"private_publication":false,"abstract":"Document clustering and topic modeling are two closely related tasks which can mutu-ally benefit each other. Topic modeling can project documents into a topic space which facilitates effective document cluster-ing. Cluster labels discovered by document clustering can be incorporated into topic models to extract local topics specific to each cluster and global topics shared by all clus-ters. In this paper, we propose a multi-grain clustering topic model (MGCTM) which inte-grates document clustering and topic model-ing into a unified framework and jointly per-forms the two tasks to achieve the overall best performance. Our model tightly couples two components: a mixture component used for discovering latent groups in document col-lection and a topic model component used for mining multi-grain topics including local topics specific to each cluster and global top-ics shared across clusters. We employ varia-tional inference to approximate the posterior of hidden variables and learn model param-eters. Experiments on two datasets demon-strate the effectiveness of our model.","bibtype":"article","author":"Xie, Pengtao and Xing, Eric P","bibtex":"@article{\n title = {Integrating Document Clustering and Topic Modeling},\n type = {article},\n websites = {https://arxiv.org/pdf/1309.6874.pdf},\n id = {7ebfb27e-4d00-3ec3-9102-961036d27501},\n created = {2018-02-05T18:53:21.704Z},\n accessed = {2018-02-05},\n file_attached = {true},\n profile_id = {371589bb-c770-37ff-8193-93c6f25ffeb1},\n group_id = {f982cd63-7ceb-3aa2-ac7e-a953963d6716},\n last_modified = {2018-02-05T18:53:25.053Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {false},\n hidden = {false},\n private_publication = {false},\n abstract = {Document clustering and topic modeling are two closely related tasks which can mutu-ally benefit each other. Topic modeling can project documents into a topic space which facilitates effective document cluster-ing. Cluster labels discovered by document clustering can be incorporated into topic models to extract local topics specific to each cluster and global topics shared by all clus-ters. In this paper, we propose a multi-grain clustering topic model (MGCTM) which inte-grates document clustering and topic model-ing into a unified framework and jointly per-forms the two tasks to achieve the overall best performance. Our model tightly couples two components: a mixture component used for discovering latent groups in document col-lection and a topic model component used for mining multi-grain topics including local topics specific to each cluster and global top-ics shared across clusters. We employ varia-tional inference to approximate the posterior of hidden variables and learn model param-eters. Experiments on two datasets demon-strate the effectiveness of our model.},\n bibtype = {article},\n author = {Xie, Pengtao and Xing, Eric P}\n}","author_short":["Xie, P.","Xing, E., P."],"urls":{"Paper":"http://bibbase.org/service/mendeley/371589bb-c770-37ff-8193-93c6f25ffeb1/file/528f7c61-7ea6-b09b-4c63-f37c42b7536f/Integrating_Document_Clustering_and_Topic_Modeling.pdf.pdf","Website":"https://arxiv.org/pdf/1309.6874.pdf"},"bibbaseid":"xie-xing-integratingdocumentclusteringandtopicmodeling","role":"author","downloads":0},"search_terms":["integrating","document","clustering","topic","modeling","xie","xing"],"keywords":[],"authorIDs":[]}