Share This Author
Combining BPM and social software: contradiction or chance?
- Selim Erol, M. Granitzer, Rainer Schmidt
- Computer ScienceJ. Softw. Maintenance Res. Pract.
- 1 October 2010
The results of the workshop on Business Process Management and Social Software (BPMS2'08), as part of the International Conference on Business process Management in Milano, show the manifold possibilities of combining concepts from Business Process management and social software.
Sequence classification for credit-card fraud detection
Robust and Collective Entity Disambiguation through Semantic Embeddings
This work proposes a new collective, graph-based disambiguation algorithm utilizing semantic entity and document embeddings for robust entity disambIGuation, and indicates that the algorithm achieves better results than non-publicly available state-of-the-art algorithms.
The InfoSky visual explorer: Exploiting Hierarchical Structure and Document Similarities
InfoSky is a system enabling users to explore large, hierarchically structured document collections using a planar graphical representation with variable magnification, and can map metadata such as document size or age to attributes of the visualisation such as colour and luminance.
HateBERT: Retraining BERT for Abusive Language Detection in English
HateBERT, a re-trained BERT model for abusive language detection in English, is introduced and a battery of experiments comparing the portability of the fine-tuned models across the datasets are discussed, suggesting that portability is affected by compatibility of the annotated phenomena.
DoSeR - A Knowledge-Base-Agnostic Framework for Entity Disambiguation Using Semantic Embeddings
This work proposes DoSeR Disambiguation of Semantic Resources, a named entity disambigsuation framework that is knowledge-base-agnostic in terms of RDF and outperforms the state-of-the-art approaches that make use of R DF knowledge bases and/or entity-annotated document knowledge bases.
Accelerating K-Means on the Graphics Processor via CUDA
- Mario Zechner, M. Granitzer
- Computer ScienceFirst International Conference on Intensive…
- 20 April 2009
An optimized k-means implementation on the graphics processing unit (GPU) is presented, demonstrating a maximum 14x speed increase to a fully SIMD optimized CPU implementation.
Measuring the quality of web content using factual information
This work presents a simple statistical quality measure that is based on facts extracted from Web content using Open Information Extraction, and uses this measure to identify featured/good articles in Wikipedia.
Efficient linear text segmentation based on information retrieval techniques
This work presents an algorithm that has a computational complexity of O(n) with n being the number of sentences in a document, and demonstrates that this approach provides comparable accuracy.
On the Beauty and Usability of Tag Clouds
- C. Seifert, Barbara Kump, W. Kienreich, Gisela Granitzer, M. Granitzer
- Computer Science12th International Conference Information…
- 9 July 2008
A family of novel algorithms for tag cloud layout is proposed and evaluation results obtained from an extensive user study and a technical evaluation enable designers to devise a combination of algorithm and parameters which produces satisfying tag cloud layouts for many application scenarios.