Sign inSign up
Identifying and Labeling Search Tasks via Query-based Hawkes Processes thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Identifying and Labeling Search Tasks via Query-based Hawkes Processes

Published on Oct 07, 20141678 Views

Liangda Li

We consider a search task as a set of queries that serve the same user information need. Analyzing search tasks from user query streams plays an important role in building a set of modern tools to imp

Research Sessions

Related categories

Data MiningKnowledge Extraction

Chapter list

Identifying and Labeling Search Tasks via Query-based Hawkes Process00:00
Search Task00:09
Consecutive Queries vs Search Tasks01:03
LDA and Query Co-occurrence02:20
Temporally weighted Co-occurrence03:20
Hawkes Process04:23
Social influence in Search Task05:09
Issues in Influence Estimation06:40
Semantic Influence07:27
A Toy Example08:15
Graphical Model Representation08:53
Data set09:16
Inference and Estimation09:33
Q-Q Plot09:59
Predictive Likelihood10:21
Query Clustering10:33
Search Task Identification10:53
Summary11:23
Q & A Thank you!11:52