Prof. Dr. Iryna Gurevych Dr. Delphine Bernhard, Johannes ... · Web 1.0 versus Web 2.0 Web 1.0 ! Web 2.0 DoubleClick --> Google AdSense mp3.com --> Napster Britannica Online --> Wikipedia

Knowledge Management for Web 2.0

Prof. Dr. Iryna Gurevych

Dr. Delphine Bernhard, Johannes Hoffart, Torsten Zesch

4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 1

1.

2.

Introduction to the topic

Related projects at UKP Lab

Outline

4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 2

3. Presentation of seminar topics

Obligatory Reading

What Is Web 2.0

Design Patterns and Business

Models for the Next Generation of

Software

by Tim O'Reilly

09/30/2005

4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 3

What happened in Fall 2001?

4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 4

Popularity of Web 2.0

4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 5

Web 1.0 versus Web 2.0

Web 1.0 ! Web 2.0

DoubleClick --> Google AdSense

mp3.com --> Napster

Britannica Online --> Wikipedia

personal websites --> blogging

domain name speculation --> search engine optimization

page views --> cost per click

screen scraping --> web services

publishing --> participation

content management systems --> wikis

directories (taxonomy) --> tagging („folksonomy“)

4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 6

05/05/08 | Computer Science Department | Ubiquitous Knowledge Processing Lab | 7/76

Central Principle of Web 2.0

Harnessing Collective Intelligence

4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 8

Harnessing Collective Intelligence

!!Hyperlinking

!!Yahoo!

!!Google

!!eBay

!!Amazon

4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 9

Hyperlinking

!!Foundation of the web

!!Users add new content, and new sites

!!Bound in to the structure of the web by other users

discovering the content and linking to it

!!Much as synapses form in the brain, with

associations becoming stronger through repetition or

intensity, the web of connections grows organically as

an output of the collective activity of all web users

4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 10

Yahoo!

!!The first great internet success story

!!Born as a catalog, or directory of links, an

aggregation of the best work of thousands, then

millions of web users

!!Moved into the business of creating many types of

content

!!A portal to the collective work of the net's users

4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 11

Google

!!Breakthrough in search

!!Undisputed search market leader

!!PageRank, a method of using the link structure of

the web rather than just the characteristics of

documents to provide better search results

4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 12

eBay

!!eBay's product is the collective activity of users

!!Grows organically in response to user activity

!!The company's role is as an enabler of a context in

which that user activity can happen

!!Competitive advantage from the critical mass of

buyers and sellers, which makes any new entrant

offering similar services significantly less attractive

4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 13

Amazon

!!The same products as competitors such as

Barnesandnoble.com

!!A science of user engagement

!!More user reviews, invitations to participate in varied

ways on virtually every page – and even more

importantly, they use user activity to produce better

search results

!!Always leads with "most popular", a real-time

computation based not only on sales but other factors

that Amazon insiders call the "flow" around products

4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 14

Further Web 2.0 Innovations

!!Wikipedia

!!del.icio.us

!!Flickr

!!Collaborative spam filtering

4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 15

Wikipedia

!!An online encyclopedia

!!An entry can be added and edited by any web user

!!A radical experiment in trust

!!Eric Raymond's dictum (originally coined in the

context of open source software) that “with enough

eyeballs, all bugs are shallow”

!!Among the top ten web sites 4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 16

Competencies of Web 2.0 Companies

•!Services, not packaged software

•!Control over unique, hard-to-recreate data sources

that get richer as more people use them

•!Trusting users as co-developers

•!Harnessing collective intelligence

•!Leveraging the long tail through customer self-

service

•!Software above the level of a single device

•!Lightweight user interfaces, development models,

AND business models

4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 17

1.

2.

Introduction to the topic

Related projects at UKP Lab

Outline

4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 18

3. Presentation of seminar topics

Related Projects at UKP Lab

!!Semantic Information Retrieval using Wikipedia, Wiktionary

!!Question Answering for E-Learning based on Social

Question & Answer plattforms

!!Wikulu – Self-organizing Wikis

!!Theseus-TEXO: Knowledge-based Infrastructures for

Internet of the Future (Web Services, Community Mining)

4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 19

4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 20

Web 2.0 as Knowledge Resource

for Natural Language Processing

NLP applications

!!???

NLP applications

!!Semantic Relatedness !! (Zesch et al., 2008)

NLP applications

!!Information Extraction !! (Ruiz-Casado et al., 2005)

!!Information Retrieval !! (Gurevych et al., 2007)

!!Named Entity Recognition !! (Bunescu & Pasca, 2006)

!!Question Answering !! (Ahn et al., 2004)

!!Text Categorization !! (Gabrilovich & Markovitch, 2006)

Wiktionary – Wikipedia‘s lexical companion

!!Language

!!Etymology

!!Pronunciation

!!Part-of-speech

!!Word senses

!!Synonyms

!!Derived Terms

!!Translations

!!Abbreviations, Antonyms,

Categories, Collocations,

Examples, Glosses,

Hypernyms, Hyponyms,

Morphology, Quotations,

Related terms, Troponyms 4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 21

Semantisches Information Retrieval

8.10.2008 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 22

Suche:

Dienstreise

….

… Geschäftsreise

…

Gesuchtes Dokument:

Mining Wikipedia Revision History for

Paraphrase Recognition

4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 23

Automatic Question Answering for eLearning

8.10.2008 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 24

Answer Retrieval and Summarization

8.10.2008 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 25

What are

Internet

Browsers

Ranked list of answers: 1.!A web browser is a software

application which … 2.!A web browser is a graphical

interface that … 3.!The most common web browsers are Firefox, Netscape,

IE, Safari, …

Opinion-Oriented Search in Social Q&A Plattforms

8.10.2008 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 26

Wikis for Knowledge Management

4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 27

•! Small

•! Well structured

•! Easy to find and add content

In the beginning ...

People like

it and add

lots of content

I can‘t find

anything!

Where do

I put this?

?

How can we solve these

problems?

Use Natural Language Processing to

support the user with his tasks:

!!Searching Information

!!Semantic Information Retrieval

!!Question Answering

!!Browsing

!!Keyphrase Extraction and

Summarization

!!Topic Detection

!!Adding content

!!Suggest similar pages where to add

the content

!!Suggest links pointing to and

originating from a new page

4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 28

How Wikulu might look like

4/20/09 | Computer Science Department | Ubiquitous Knowledge Processing Lab | © Prof. Dr. Iryna Gurevych | 29

„Wikulu“ - Hawaiian for organize [‚kukulu‘] fast [‚wiki‘]