3 papers
cs.CL2020
On the Replicability of Combining Word Embeddings and Retrieval Models
Luca Papariello, Alexandros Bampoulidis, Mihai Lupu
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 t…
cs.CR2019
An Abstract View on the De-anonymization Process
Alexandros Bampoulidis, Mihai Lupu
Over the recent years, the availability of datasets containing personal, but anonymized information has been continuously increasing. Extensive research has revealed that such data…
cs.IR2017
Character-based Neural Embeddings for Tweet Clustering
Svitlana Vakulenko, Lyndon Nixon, Mihai Lupu
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…