Applying unsupervised learning in creating language models for information retrieval and machine translation

author:Timo Honkela, Helsinki University of Technology
published: July 21, 2008,   recorded: June 2008,   views: 188
Categories
You might be experiencing some problems with Your Video player.

Slides

Slides
0:00 Language Modeling Using Unsupervised Learning Methods with Applications in IR and MT
1:09 Focus
1:49 Agenda
2:38 Case Studies
3:57 Background
5:50 Agenda - Learning Paradigms
5:57 Learning Paradigms
6:24 Supervised Learning
7:05 Unsupervised Learning
8:54 Agenda - Philosophical and Practical Motivation
9:11 Traditional Formalization
10:11 Nature of Traditional Knowledge Representations
11:00 Traditional Formalization of Meaning, Cont'd
11:48 Neglected Pattern Recognition Processes
12:09 “Symbols˝ versus “Reality”
13:07 Formal Semantics: Early Wittgenstein
14:27 Example: Color Naming
16:05 Experiential Grounding of Human Knowledge
17:15 General Communication System and Measuring Information
18:02 Weaver on Shannon
18:40 Agenda - Overview of Unsupervised Learning Methods for Language Modeling
19:20 Modeling Language Learning
20:45 Language in Context
21:27 Modeling Distributional Similarity: Word Space Models
22:53 Agenda - Case Studies
23:05 Case Studies - 1
23:18 Self-Organizing Map
25:17 Self-Organizing Process
25:49 SOM Analysis of Grimm Fairy Tales
27:05 Emergent Implicit Categories
28:44 Map of Verbs
29:15 Emergence of Ontological Relations
31:09 Map of Documents: WEBSOM
32:25 Application Example: Document Map of Research
36:45 WEBSOM: Modes of Use
37:26 Application Example: Document Map of Research
38:15 WEBSOM: Modes of Use
41:50 Case Studies - 2
42:21 Text Mining Based on the SOM for Qualitative Research
43:14 Coherent Project Views
43:47 Scattered Project Views
45:16 Case Studies - 3
46:05 Independent Component Analysis
50:57 Word-Context Input Matrix
51:29 Word ICA - 1
52:16 Word ICA: Example
53:42 Word ICA - 2
54:43 Word ICA - 3
56:41 Relation to Koehn's Presentation
60:40 Time for a Break ...
61:57 Word ICA - 3
63:51 Application Example: Document Map of Research
63:57 - Questions

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Lecture popularity: You need to login to cast your vote.

 Watch videos:   (click on thumbnail to launch)

Watch Part 1
Part 1 1:07:31 Flash video Slides Windows Media video
!NOW PLAYING
Watch Part 2
Part 2 1:16:22 Flash video Windows Media video

Link this page  

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Write your own review or comment:

make sure you have javascript enabled or clear this field: