en-de
en-es
en-fr
en-pt
en-sl
en
en-zh
0.25
0.5
0.75
1.25
1.5
1.75
2
TopicFlow Model: Unsupervised Learning of Topic-specific Influences of Hyperlinked Documents
Published on May 06, 20114093 Views
Popular algorithms for modeling the influence of entities in networked data, such as PageRank, work by analyzing the hyperlink structure, but ignore the contents of documents. However, often times,
Related categories
Chapter list
TopicFlow Model:Modeling topic-specific global influence of hyperlinked documents00:00
Introduction: Modeling global influence00:34
Introduction: Modeling topicalglobal influence01:07
TopicFlow model01:24
TopicFlow model: Independent topic sources02:14
TopicFlow model: Single source for all topics03:01
TopicFlow model: definitions03:08
TopicFlow model: What the flow means04:31
TopicFlow model: Intuition05:27
TopicFlow model: How does it model global topical influence?06:16
Topic Sensitive PageRank vs. TopicFlow07:37
TopicFlow model: Learning and Inference (1)09:25
TopicFlow model: Learning and Inference (2)09:59
TopicFlow model: Learning and Inference (3)10:08
A statistical Approach to Sense Disambiguation 10:38
Empirical analysis on ACL data12:28
Citation Recommendation on ACL: results13:32
Case 1: CORA Document Completion Log-likelihood14:26
Case 2: ACL Document Completion Log-likelihood14:39
Conclusions14:50