Stage-oe-small.jpg

Vortrag Kolloquium Angewandte Informatik Dr. Michael Cochez: Unterschied zwischen den Versionen

Aus Aifbportal
Wechseln zu:Navigation, Suche
(Die Seite wurde neu angelegt: „{{Veranstaltung |Titel DE=Vortrag Kolloquium Angewandte Informatik Dr. Michael Cochez |Titel EN=Vortrag Kolloquium Angewandte Informatik Dr. Michael Cochez |Be…“)
 
Zeile 1: Zeile 1:
 
{{Veranstaltung
 
{{Veranstaltung
|Titel DE=Vortrag Kolloquium Angewandte Informatik Dr. Michael Cochez
+
|Titel DE=Knowledge Graph Embedding
|Titel EN=Vortrag Kolloquium Angewandte Informatik Dr. Michael Cochez
+
|Titel EN=Knowledge Graph Embedding
|Beschreibung DE=folgt
+
|Beschreibung DE=Recently graph embeddings have been taken up by the community as a tool to solve various tasks in machine learning and the general AI community.
|Beschreibung EN=folgt
+
In this talk I will give a gentle introduction to the topic and also give some pointers to currently ongoing research.
 +
We start from looking at why graph embeddings are needed in the first place and how they could be used.  We will then focus on graphs containing a large variety of information, typically called knowledge graphs, often represented in RDF. These graphs are hard to embed (compared to e.g., uniform simple networks) because they contain multiple edge and vertex types, relation directionality, literals, etc.
 +
What we will cover are a few basic techniques on how these embeddings can be computed. We plan to look into at least one example of translational based methods, one from matrix decomposition, and methods based on co-occurrence and statistical information. Finally we will discuss about a couple of open problems and some of the topics currently worked on.
 +
|Beschreibung EN=Recently graph embeddings have been taken up by the community as a tool to solve various tasks in machine learning and the general AI community.
 +
In this talk I will give a gentle introduction to the topic and also give some pointers to currently ongoing research.
 +
We start from looking at why graph embeddings are needed in the first place and how they could be used.  We will then focus on graphs containing a large variety of information, typically called knowledge graphs, often represented in RDF. These graphs are hard to embed (compared to e.g., uniform simple networks) because they contain multiple edge and vertex types, relation directionality, literals, etc.
 +
What we will cover are a few basic techniques on how these embeddings can be computed. We plan to look into at least one example of translational based methods, one from matrix decomposition, and methods based on co-occurrence and statistical information. Finally we will discuss about a couple of open problems and some of the topics currently worked on.
 
|Veranstaltungsart=Kolloquium Angewandte Informatik
 
|Veranstaltungsart=Kolloquium Angewandte Informatik
 
|Start=2019/03/15 14:00:00
 
|Start=2019/03/15 14:00:00
Zeile 9: Zeile 15:
 
|Gebäude=05.20
 
|Gebäude=05.20
 
|Raum=3A-11.2
 
|Raum=3A-11.2
 +
|Vortragender=Dr. Michael Cochez
 +
|PDF=Cochez 15-03-2019.pdf
 
|Forschungsgruppe=Information Service Engineering
 
|Forschungsgruppe=Information Service Engineering
 
|In News anzeigen=Ja
 
|In News anzeigen=Ja
 
}}
 
}}

Version vom 7. März 2019, 09:42 Uhr

Knowledge Graph Embedding

Veranstaltungsart:
Kolloquium Angewandte Informatik




Recently graph embeddings have been taken up by the community as a tool to solve various tasks in machine learning and the general AI community. In this talk I will give a gentle introduction to the topic and also give some pointers to currently ongoing research. We start from looking at why graph embeddings are needed in the first place and how they could be used. We will then focus on graphs containing a large variety of information, typically called knowledge graphs, often represented in RDF. These graphs are hard to embed (compared to e.g., uniform simple networks) because they contain multiple edge and vertex types, relation directionality, literals, etc. What we will cover are a few basic techniques on how these embeddings can be computed. We plan to look into at least one example of translational based methods, one from matrix decomposition, and methods based on co-occurrence and statistical information. Finally we will discuss about a couple of open problems and some of the topics currently worked on.

(Dr. Michael Cochez)




Start: 15. März 2019 um 14:00
Ende: 15. März 2019 um 15:30


Im Gebäude 05.20, Raum: 3A-11.2

Veranstaltung vormerken: (iCal)


Veranstalter: Forschungsgruppe(n) Information Service Engineering
Information: Media:Cochez 15-03-2019.pdf