Naslov
Prostorno-vremensko predstavljanje riječi
(Spatio-Temporal Word Embeddings)

Autori
Kraljević, Željko

Vrsta, podvrsta i kategorija rada
Ocjenski radovi, diplomski rad, diplomski

Fakultet
Fakultet elektrotehnike i računarstva

Mjesto
Zagreb

Datum
24.02

Godina
2016

Stranica
26

Mentor
Golub, Marin

Ključne riječi
vektorske reprezentacije ; pronalaženje teme ; grupiranje ; vrijeme ; mikro-blogovi ;
(distributed representation ; topic detection ; time ; clustering ; micro-blogs ;)

Sažetak
Latent Topic Models are a powerful tool for classifying, clustering and representing documents. For dynamic collections, we need to model both temporal and topical evolution. In this work, we present two models that use a continuous time distribution and that represent words as trajectories in a continuous space. We perform experiments on Twitter data and compare our model to some state of the art models in this field, but also a simpler baseline, all of this shows the potential of our model,

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA