Resource – Paper 308

An Entity Relatedness Test Dataset

José Eduardo Talavera Herrera, Marco Antonio Casanova, Bernardo Pereira Nunes, Luiz André P. Paes Leme and Giseli Rabello Lopes

Resource

clock_eventOctober 23, 2017, 15:00.
house Lehár 4
download Download paper (preprint)

Abstract

A knowledge base stores descriptions of entities and their relationships, often in the form of a very large RDF graph, such as DBpedia or Wikidata. The entity relatedness problem refers to the question of computing the relationship paths that better capture the connectivity between a given entity pair. This paper describes a dataset created to support the evaluation of approaches that address the entity relatedness problem. The dataset covers two familiar domains, music and movies, and uses data available in IMDb and last.fm, which are popular reference datasets in these domains. The paper describes in detail how sets of entity pairs from each of these domains were selected and, for each entity pair, how a ranked list of relationship paths was obtained.

1
Leave a Reply (Click here to read the code of conduct)

avatar
1 Comment threads
0 Thread replies
0 Followers
 
Most reacted comment
Hottest comment thread
1 Comment authors
anonymousRecent comment authors
  Subscribe  
newest oldest most voted
Notify of
anonymous
Guest
anonymous

won’t defining entity relatedness by means of graphs (with restrictions) introduce biases?
How likely is it that the presented approach generalizes to other domains, given that it’s only focusing on the (very similar) movie and music domain?

related work could be improved, how does this work compare to:
https://dl.acm.org/citation.cfm?id=2874488
https://hpi.de/fileadmin/user_upload/fachgebiete/meinel/papers/Web_3.0/2015_BobicWaitelonisSack.pdf
https://link.springer.com/chapter/10.1007%2F978-3-540-88564-1_39?LI=true
http://www.aaai.org/Papers/IJCAI/2007/IJCAI07-259.pdf
https://dl.acm.org/citation.cfm?id=1708133