de.mpg.escidoc.pubman.appbase.FacesBean
Deutsch
 
Hilfe Wegweiser Impressum Kontakt Einloggen
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT

Freigegeben

Hochschulschrift

Estimating Event Focus Time with Distributed Representation of Words

MPG-Autoren
http://pubman.mpdl.mpg.de/cone/persons/resource/persons209043

Das,  Supratim
Databases and Information Systems, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons44119

Berberich,  Klaus
Databases and Information Systems, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons79375

Mishra,  Arunav
Databases and Information Systems, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons45461

Setty,  Vinay
Databases and Information Systems, MPI for Informatics, Max Planck Society;

Externe Ressourcen
Es sind keine Externen Ressourcen verfügbar
Volltexte (frei zugänglich)
Es sind keine frei zugänglichen Volltexte verfügbar
Ergänzendes Material (frei zugänglich)
Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar
Zitation

Das, S., Berberich, K., Klakow, D., Mishra, A., & Setty, V. (2017). Estimating Event Focus Time with Distributed Representation of Words. Master Thesis, Universität des Saarlandes, Saarbrücken.


Zitierlink: http://hdl.handle.net/11858/00-001M-0000-002D-DFF1-7
Zusammenfassung
Time is an important dimension as it aids in disambiguating and understanding news- worthy events that happened in the past. It helps in chronological ordering of events to understand its causality, evolution, and ramifications. In Information Retrieval, time alongside text is known to improve the quality of search results. So, making use of the temporal dimensionality in the text-based analysis is an interesting idea to explore. Considering the importance of time, methods to automatically resolve temporal foci’s of events are essential. In this thesis, we try to solve this research question by training our models on two different kinds of corpora and then evaluate on a set of historical event-queries.