東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Pachinko allocation: DAG-structured ...

Li, Wei.

FindBook

Google Book

Amazon

博客來

Pachinko allocation: DAG-structured mixture models of topic correlations.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Pachinko allocation: DAG-structured mixture models of topic correlations./
作者:	Li, Wei.
面頁冊數:	100 p.
附註:	Adviser: Andrew McCallum.
Contained By:	Dissertation Abstracts International68-11B.
標題:	Artificial Intelligence. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3289214
ISBN:	9780549330233

Pachinko allocation: DAG-structured mixture models of topic correlations.
Li, Wei.

Pachinko allocation: DAG-structured mixture models of topic correlations. - 100 p.

Adviser: Andrew McCallum.

Thesis (Ph.D.)--University of Massachusetts Amherst, 2007.

Statistical topic models are increasingly popular tools for summarization and manifold discovery in discrete data. However, the majority of existing approaches capture no or limited correlations between topics. We propose the pachinko allocation model (PAM), which captures arbitrary, nested, and possibly sparse correlations between topics using a directed acyclic graph (DAG). We present various structures within this framework, different parameterizations of topic distributions, and an extension to capture dynamic patterns of topic correlations. We also introduce a non-parametric Bayesian prior to automatically learn the topic structure from data. The model is evaluated on document classification, likelihood of held-out data, the ability to support fine-grained topics, and topical keyword coherence. With a highly-scalable approximation, PAM has also been applied to discover topic hierarchies in very large datasets.

ISBN: 9780549330233Subjects--Topical Terms:

769149
Artificial Intelligence.

Pachinko allocation: DAG-structured mixture models of topic correlations.
LDR:02042nam 2200337 a 45 001 958973
005 20110704
008 110704s2007 ||||||||||||||||| ||eng d
020 $a 9780549330233
035 $a (UMI)AAI3289214
035 $a AAI3289214
040 $a UMI $c UMI
100 1 $a Li, Wei. $3 884990
245 1 0 $a Pachinko allocation: DAG-structured mixture models of topic correlations.
300 $a 100 p.
500 $a Adviser: Andrew McCallum.
500 $a Source: Dissertation Abstracts International, Volume: 68-11, Section: B, page: 7440.
502 $a Thesis (Ph.D.)--University of Massachusetts Amherst, 2007.
520 $a Statistical topic models are increasingly popular tools for summarization and manifold discovery in discrete data. However, the majority of existing approaches capture no or limited correlations between topics. We propose the pachinko allocation model (PAM), which captures arbitrary, nested, and possibly sparse correlations between topics using a directed acyclic graph (DAG). We present various structures within this framework, different parameterizations of topic distributions, and an extension to capture dynamic patterns of topic correlations. We also introduce a non-parametric Bayesian prior to automatically learn the topic structure from data. The model is evaluated on document classification, likelihood of held-out data, the ability to support fine-grained topics, and topical keyword coherence. With a highly-scalable approximation, PAM has also been applied to discover topic hierarchies in very large datasets.
590 $a School code: 0118.
650 4 $a Artificial Intelligence. $3 769149
650 4 $a Computer Science. $3 626642
650 4 $a Statistics. $3 517247
690 $a 0463
690 $a 0800
690 $a 0984
710 2 $a University of Massachusetts Amherst. $b Computer Science. $3 1023848
773 0 $t Dissertation Abstracts International $g 68-11B.
790 $a 0118
790 1 0 $a Blei, David $e committee member
790 1 0 $a Croft, W. Bruce $e committee member
790 1 0 $a Mahadevan, Sridhar $e committee member
790 1 0 $a McCallum, Andrew, $e advisor
790 1 0 $a Staudenmayer, John $e committee member
791 $a Ph.D.
792 $a 2007
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3289214