Academic report of Prof. Herwig Unger, Hagen University, Germany

Source:SIST  Author:Yan Jiang  Date:2018-09-14  Click:96

Academic report of of Prof. Herwig Unger, Hagen University, Germany

(Title):On Evolving Text Centroids

(Speaker): Prof.Herwig Unger

(Time) 4:00pm, Wednesda, 1 August, 2018

(Venue)X9431 No. 9 Building, Xipu Campus of Southwest Jiaotong University

(Chair)Prof.TianRui Li

Outline of the Talk:

From the literature, a plentitude of approaches to compare and categorise text documents are known. Regarding their exactness and computational costs they differ significantly. The major disadvantage of most of them is not to utilize the general knowledge a human reader may have. Furthermore, these methods are usually not able to process and consider documents as sequences of words, whereby different sequences may significantly determine a text’s contents and meaning — as well as quality.

Centroid terms has been introduced to be single words that semantically and topically characterise text documents and thus can act as their very compact representation in automatic text processing tasks. In this talk, a novel brain-inspired approach is presented to first simplify the determination of centroid terms and second to generalise the underlying concept at the same time. As the precision of the centroid-based text representation is improved by this means as well, new applications for centroids are derived, too.

The talk shall be an introduction for a deeper discussion on the following questions:

* How different reader's backgrounds and thier evolution may be modelled?

* How an impression about the topic of a document may develop?

* How the impacts of two or more read documents may interfere?
(Short Biography of the Speaker):

Prof. Dr.-Ing. habil. Herwig Unger got his PhD with a work on Petri Net transformation in 1994 from the Technical University of Ilmenau and his habilitation with a work on large distributed systems from the University of Rostock in 2000. Since 2006, he is a full professor at the FernUniversität in Hagen and the head of the Chair of Communication Networks. His research interests are in self-organization, adaptive and learning systems, Internet algorithms and simulation systems.