Title: Aucun titre de diapositive
1(No Transcript)
2(No Transcript)
3(No Transcript)
4(No Transcript)
5(No Transcript)
6(No Transcript)
7(No Transcript)
8(No Transcript)
9GENERAL ARCHITECTURE (indexing and retrieval)
10GENERAL ARCHITECTURE (general ontology
construction)
11Audiovisual Grounded Ontology project AVONTO
- Object ontology reworked from WordNet
12(No Transcript)
13(No Transcript)
14(No Transcript)
15Examples of interrogation for extraction
representative images
Google image search using the French word
avocat
Google image search using the English word
avocado
The word is now not ambiguous but images show
both the fruit and the tree
16Toward a more focused interrogation
Google image search using the English word
avocado tree
Google image search using the English word
avocado fruit
17An other example of disambiguation using the
ontology
18Images tagged by dog are too much ambiguous
- Current annotation dog from Picsearch
-
19The concept of dog is much more well
represented by the addition of images linked with
the leaves of the taxonomy
20Filtering retrieved images
21clustering of Objects
22Background Removal after segmentation
23Automatic Segmentation Results
24Choice of good representatives (we need not the
full set of images but good set of prototypes)
25Use of commentaries in video
26Semantics extraction from texts
Affenpinscher Airedale terrier Akita Inu
American staffordshire terrier
27Semantics extraction from texts
Use results of syntactic analysis to extract
semantics
- you have decided to adopt a dog
- ?A dog can be adopted
- for active and big sized dog
- A dog can be active
- A dog can have a big size
- Dogs like medulla marrowbones
- A dog like marrowbones
- when the dog wags tail, it is happy
- A dog can be happy
- When a dog is happy it wags tail
- .
28The color of things
29Multilingual aspect
Spanish and Italian wordnet are aligned with a
part of English wordnet
- ?Use several bilingual dictionaries to add
languages - Ex heifer (EN), giovenca or manza (IT), novilla
(ES) - gives génisse (FR) using EN-FR, IT-FR, ES-FR
dictionary - Use bilingual dictionaries for the most precise
concepts that have no translation ambiguities - Ex racoon (EN) gives raton laveur (FR)
- Use scientific names to find translations into
languages for animals, plants, - Ex oryx gazella (Sc) gives orice gazella (IT)
30Multilingual aspect in the ontology
ltowlClass rdfabout"bullock__1"gtltrdfscomment
rdfdatatype"http//www.w3.org/2001/XMLSchemastr
ing"gt Italian Translation manzo__2
lt/rdfscommentgt ltrdfscomment rdfdatatype"http/
/www.w3.org/2001/XMLSchemastring"gt Spanish
Translation novillo__2 lt/rdfscommentgtlt/owlClas
sgt
31State of the construction in our lab
Images 4800 objects 1.2 Million
pictures Automatically collected, segmented,
clustered 250 Gbytes Video 6 channels 60
video/day 2GB/day Processing by LIMSI/VECSYS
speech to text technologies
32State of the construction in our lab
Gregory Grefenstette 2006-2007 Morphosyntactic
(dependency relations) of the full French
web Extraction of semantics from this
analysis 2007-2008 Same processing for English
33Conclusion
Very huge task Necessitate the combination of
various knowledge Collaboration of several teams
at the European level (even international) Link
with other initiative like UNL (Universal
word) Need a big computing and storage
capacity ? Super computer, large clusters, grid