Top Banner
A Brief Survey of Multimedia Annotation Localisation on the Web of Linked Data Gary Lefman 1 David Lewis 1 Felix Sasaki 2 [email protected] [email protected] cd.ie felix.sasaki@df ki.de 1 CNGL the Centre for Global Intelligent Content, Trinity College Dublin, Ireland 2 Language Technology Lab, German Research Centre for Artificial
17

Multimedia Annotation Localisation on the Web of Linked Data

Feb 21, 2017

Download

Social Media

Gary Lefman
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: Multimedia Annotation Localisation on the Web of Linked Data

A Brief Survey of Multimedia Annotation Localisation on the Web of Linked Data

Gary Lefman1

David Lewis1

Felix Sasaki2 [email protected]

[email protected]

[email protected]

e

1CNGL the Centre for Global Intelligent Content, Trinity College Dublin, Ireland2Language Technology Lab, German Research Centre for Artificial Intelligence (DFKI),

Germany

Page 2: Multimedia Annotation Localisation on the Web of Linked Data

A brief survey

feasibility ofmultilingual annotation on social mediausing linked data

very^

Page 3: Multimedia Annotation Localisation on the Web of Linked Data

Why are we looking at this?

role of localisation multimedia ontologies linking annotated resourcesacross languages

Page 4: Multimedia Annotation Localisation on the Web of Linked Data

Rectangle:140,170,50,50 Text: “tree”Author: “Jane Doe”Locale: <Unknown>

tree

Social Media Platform A

The annotation disconnect

Page 5: Multimedia Annotation Localisation on the Web of Linked Data

Rectangle:212,182,50,50 Text: “coeden”Author: “John Doe”Locale: <Unknown>

coedenSocial Media Platform B

The annotation disconnect

Page 6: Multimedia Annotation Localisation on the Web of Linked Data

tree

coeden

Search for:“Baum”Locale:

de-DE

? “Baum”

Plat

form

BPl

atfo

rm A

The annotation disconnect

Page 7: Multimedia Annotation Localisation on the Web of Linked Data

Flickr

Resource

Page 8: Multimedia Annotation Localisation on the Web of Linked Data

Annotation

No Ontology

Resource

Folksonomy

Monolingual

Monolingual

“African Lion”

“Afrikanskt Lejon”

Flickr

Page 9: Multimedia Annotation Localisation on the Web of Linked Data

Resource

Flickr

Page 10: Multimedia Annotation Localisation on the Web of Linked Data

Flickr – what did we learn?

monolingual platformno hint of an ontologyheterogeneous folksonomiessimple keyword tagging

Page 11: Multimedia Annotation Localisation on the Web of Linked Data

Flickr – what did we learn?

Page 12: Multimedia Annotation Localisation on the Web of Linked Data

Flickr – what did we learn?

Page 13: Multimedia Annotation Localisation on the Web of Linked Data

Flickr – what did we learn?

monolingual annotations in siloesuncontrolled “machine tags”

namespace:predicate=value

Page 14: Multimedia Annotation Localisation on the Web of Linked Data

Further research

linguistically linkedfolksonomic multimedia annotationacross social media platforms

Page 15: Multimedia Annotation Localisation on the Web of Linked Data

Search for:“Löwe”Locale:

de-DE

“Löwe”

LLOD

http://flickr.com/photos/tags/dc:subject=African%20Lionhttp://flickr.com/photos/tags/dc:subject=Afrikanskt%20Lejonhttp://tumblr.com/tagged/African%20Lion

Further research

Page 16: Multimedia Annotation Localisation on the Web of Linked Data

Better Utilisation of Dublin Corehttp://flickr.com/photos/tags/dc:subject=African%20Lion&dc:language=en-ZA

Integrate Media Fragments URIhttp://flickr.com/photos/tags/dc:subject=African%20Lion&dc:language=en-ZA&xywh=0,0,250,400

Utilise MediaONThttp://flickr.com/photos/tags/ma:keyword=African%20Lion&ma:language=en-ZA

Further research

Page 17: Multimedia Annotation Localisation on the Web of Linked Data

Questions?

Gary Lefman1

David Lewis1

Felix Sasaki2

[email protected] [email protected] [email protected]

1CNGL the Centre for Global Intelligent Content, Trinity College Dublin, Ireland2Language Technology Lab, German Research Centre for Artificial Intelligence (DFKI),

Germany