Software


Hermes – A Distributed-messaging Tool for NLP

The Hermes tool is based on the IEEE BigData’16 paper entitled Advancing NLP via a distributed-messaging approach.

Hermes is a novel NLP tool that overcomes two main limitations of existing solutions: (i) the architectures underlying existing systems do not satisfy critical requirements of large-scale processing, completeness, and versatility, and (ii) the algorithms typically employed for entity recognition and disambiguation—a core task common to all modern NLP systems—are still not well-suited for deployment in a real industrial environment, for evident issues of efficiency and result interpretability.
By employing an efficient and extendable distributed-messaging architecture, Hermes achieves the critical requirements of large-scale processing, completeness, and versatility. Moreover, Hermes includes an entity-disambiguation algorithm
enhanced with a two-level hashing-based approximation technique to considerably improve efficiency, as a well as a densest-subgraph-extraction method to increase result interpretability.

The Hermes tool is free for research, academic and non-profit making purposes only. If you use the tool for your work and got something published please include the above citation. The tool may not be sold or redistributed without prior approval.
Email me to get URL and access credentials!




JPCE – A Java implementation of Projective Clustering Ensembles

The Projective Clustering Ensembles project is based on the SIGMOD’11 paper entitled Advancing Data Clustering via Projective Clustering Ensembles.

JPCE is a Java software package that implements PCE. This package is free for research, academic and non-profit making purposes only. If you use this piece of software for your work and got something published please include the above citation. The software may not be sold or redistributed without prior approval. One may make copies of the software for their use provided that the copies, are not sold or distributed, are used under the same terms and conditions. As unestablished research software, this code is provided on an “as is” basis without warranty of any kind, either expressed or implied. The downloading, or executing any part of this software constitutes an implicit agreement to these terms. These terms and conditions are subject to change at any time without prior notice.

Download the JPCE (v1.0) package. This includes documentation on JPCE, and all datasets and results presented in the SIGMOD’11 paper. Additionally, the ensembles data files used for experiments in the SIGMOD’11 paper can be downloaded from here. Source code is instead available here.




JCLUData – A Java software for clustering uncertain data

JCLUData contains an implementation of three algorithms for clustering uncertain data, which were originally defined and described in the following peer-reviewed scientific publications:

Please access the software here.