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
Representing Text – from characters to logic
Published on Sep 12, 20114059 Views
People use natural language and write texts to express themselves. For the purpose of text processing, text can be represented in different ways ranging from simply characters to capturing knowledge f
Related categories
Chapter list
Representing Text –from characters to logic00:00
Outline00:42
Motivation00:57
Document categorization02:09
Easy decision problems require simple data representation03:14
Harder decision problems require better data representation05:07
Hard decision problems require sophisticated data representation (1)05:42
Hard decision problems require sophisticated data representation (2)05:53
Representing Text06:17
Key paradigms when dealing with data06:18
How different research areas approach text? (1)07:25
How different research areas approach text? (2)07:59
Levels of text representations (1)08:58
Levels of text representations (2)10:21
Levels of text representations: Character11:52
Language identification12:19
Levels of text representations: Vector-space model17:13
Vector-space model level17:15
Bag-of-Words document representation18:09
Similarity between BoW vectors18:48
Document Clustering Task19:59
Context Sensitive Search20:42
Search21:04
Example – Searching for "dolphin"21:19
Context sensitive search (1)21:56
SearchPoint28:50
Main advantages28:54
News Visualization29:25
Topic landscape of the query "Clinton" from Reuters news 1996-199729:26
Visualization of social relationships between "Clinton" and other entities31:16
Topic Trends Tracking of the documents including "Clinton"31:39
WW2 query "Pearl Harbor" into NYTimes archive32:51
WW2 query "Belgrade" into NYTimes archive34:12
WW2 query "Normandy" into NYTimes archive35:09
Levels of text representations: Full-parsing35:30
Full-parsing level35:40
AnswerArt35:51
AnswerArt - System Architecture36:07
AnswerArt using Medline (1)36:53
AnswerArt using Medline (2)37:46
AnswerArt using Medline (3)38:10
AnswerArt using Medline (4)38:23
AnswerArt using ASFA (1)38:56
AnswerArt using ASFA (2)39:09
Natural language text enrichment39:50
Text enrichment with40:07
Enrycher Service40:27
Entity resolution in text41:25
Enrycher Service Dependencies41:28
Enrycher - demo (1)41:33
Enrycher - demo (2)41:56
Enrycher - demo (3)42:22
Enrycher - demo (4)44:59
Levels of text representations: Ontologies / First order theories45:11
Ontologies level45:13
Cyc Knowledge Base and Reasoning45:39
The Cyc Ontology45:41
Cyc High-level Architecture46:54
Cyc KB Extended w/Domain Knowledge (1)47:33
Cyc KB Extended w/Domain Knowledge (2)48:33
Example of automatic translating text into Cyc Logic48:48
Representing knowledge in logic (X-Like project)50:39
Further references ...51:26
References to some Text-Mining books51:27
Books on Semantic Technologies51:38
References to the main conferences51:45
Videolectures.net52:08