boost your search with semantic technology
DESCRIPTION
MediaLoep combines documents readily available within the broadcasting company (subtitles, news preparation, ...) with semantic web technology to create a powerfull media search application. Presented at EBU Production Technology Seminar 2011TRANSCRIPT
EBU Production Technology Seminar 2011
Karel BraeckmanVrt-medialab
1Vrt-Medialab
VRT is the Flemish Public Broadcaster
3 TV-channels, 5 radio channels
VRT-medialab is the research department
creation, distribution and management of media content
2Vrt-Medialab
Lots of audio and video material illustrating our cultural heritage.
Also includes new material (news clips, …)
Used by programme-researchers & journalists
3VRT-medialab
Vrt-Medialab 4
The problem of media search MediaLoep project
Re-using production metadata Linking to the semantic web
Vrt-Medialab 5
The problem of media search MediaLoep project
Re-using production metadata Linking to the semantic web
Not self-descriptive → we need metadata
Video / Audio are continuous media with a time-dimension
Series: FlikkenKeywords: violence, robberyDescription: Robbery on shop. Attacker hits shop owner with gun.
6VRT-medialab
Not self-descriptive Video / Audio are continuous media with a
time-dimension → we prefer time-coded metadata
00’00”>01’43”Robbery on shop
01’43”>04’20”Police agent looks worried
35’00”>36’33”Observation by police
7VRT-medialab
35’00”>36’33”Observation by police
8VRT-medialab
Basis9Vrt-Medialab
Ardome10Vrt-Medialab
Not enough detailed annotations available
◦ “X spits on the ground after Y makes a goal”◦ The entire dialogue so we can search for quotes◦ Labels, locations, links, maps, photographs, …
as the creation of these annotations is very time consuming.
Vrt-Medialab 11
Vrt-Medialab 12
The problem of media search MediaLoep project
Re-using production metadata Linking to the semantic web
Vrt-Medialab 13
Vrt-Medialab 14
The problem of media search MediaLoep project
Re-using production metadata Linking to the semantic web
News Rundown with auto-cue texts, overlay labels, …
EPG data contains a summary of the programme, the broadcast dates, …
A drama script contains dialogues and actions, …
Subtitles ~ transcript of spoken text
15Vrt-Medialab
Vrt-Medialab 16
Information added by an archivistkeywords
textual description
other fields
Vrt-Medialab 17
Information added by the news preparation:
overlay captions
autocue text
links to other items inthis news broadcast
Vrt-Medialab 18
Information added by the subtitles:
time-coded transcriptof the dialogue
Vrt-Medialab 19
Vrt-Medialab 20
The problem of media search MediaLoep project
Re-using production metadata Linking to the semantic web
Archivists add thesaurus keywords to clips
By linking these keywords to a thesaurus, we can make the search system smarter
Vrt-Medialab 21
GenevaObama, BarackEurope…
Geneva → coordinates on a map?Obama, Barack → a picture?…
Vrt-Medialab 22
Geneva country Switzerland
15.86 km2area
Public knowledge bases provide information about resources using ‘triples’.
Vrt-Medialab 23
Geneva country Switzerland
15.86 km2area
Geneva
latitude 46° 12' 0" N
sameAs
Links to the same resource in other knowledge bases can be created.
GeoNames
Vrt-Medialab 24
A network of linked knowledge is created.
Vrt-Medialab 25
We linked MediaLoep to DBpedia, which is in turn linked to many other knowledge bases.
MediaLoep
Vrt-Medialab 26
AALMOEZENIERAALST
AALTERDE WEVER, BART
GENEVA…
VRT-Thesaurus DBpedia / Wikipedia MediaLoep
Vrt-Medialab 27
Information added by the semantic web:
Vrt-Medialab 28
Improved search by combining existing information.
Enhanced results visualization and semantic query suggestions by coupling to the semantic web.
Vrt-Medialab 29