Zobrazeno 1 - 10
of 381
pro vyhledávání: '"Lupu Mihai"'
We replicate recent experiments attempting to demonstrate an attractive hypothesis about the use of the Fisher kernel framework and mixture models for aggregating word embeddings towards document representations and the use of these representations i
Externí odkaz:
http://arxiv.org/abs/2001.04484
Autor:
LUPU, Mihai1 mihai.lupu@cig.ase.ro, GHICA, Magda1 ghicamagda14@stud.ase.ro, NĂSTASE, Cornelia1 nastasecornelia12@stud.ase.ro
Publikováno v:
Audit Financiar. 2024, Vol. 22 Issue 174, p249-359. 34p.
Autor:
Bampoulidis, Alexandros, Lupu, Mihai
Over the recent years, the availability of datasets containing personal, but anonymized information has been continuously increasing. Extensive research has revealed that such datasets are vulnerable to privacy breaches: being able to reveal sensitiv
Externí odkaz:
http://arxiv.org/abs/1902.09897
Autor:
Lupu, Mihai1 mihai.lupu@cig.ase.ro
Publikováno v:
Proceedings of the International Conference on Business Excellence. 2024, Vol. 18 Issue 1, p142-153. 12p.
Publikováno v:
In Revista Portuguesa de Cardiologia December 2022 41(12):1037-1046
Autor:
Lupu, Mihai
Publikováno v:
Jurnalul de Studii Juridice / Journal of Legal Studies. XVII(3-4):36-47
Externí odkaz:
https://www.ceeol.com/search/article-detail?id=1132388
We explore the use of unsupervised methods in Cross-Lingual Word Sense Disambiguation (CL-WSD) with the application of English to Persian. Our proposed approach targets the languages with scarce resources (low-density) by exploiting word embedding an
Externí odkaz:
http://arxiv.org/abs/1711.06196
Recent advances in neural word embedding provide significant benefit to various information retrieval tasks. However as shown by recent studies, adapting the embedding models for the needs of IR tasks can bring considerable further improvements. The
Externí odkaz:
http://arxiv.org/abs/1707.06598
In this paper we show how the performance of tweet clustering can be improved by leveraging character-based neural networks. The proposed approach overcomes the limitations related to the vocabulary explosion in the word-based models and allows for t
Externí odkaz:
http://arxiv.org/abs/1703.05123