|
|
|
-
Project: SPIGA - Language-independent personalized information provision with global orientation
( Current )
The goal of the project SPIGA is the development an information service that automatically creates document collections for semantically described topics. Such a service can be used in products such as personalized newsletters or welcome pages, or in press reviews. The idea of this project is to exploit both the semantics and multilinguality of the news articles. Working within the news domain has the advantage that often the same news event is covered in different languages, such that there are multiple text variants of the same information. The core approach focuses on the extraction of knowledge - or rather semantic concepts - from news, in order to link the news documents. Each news event is thus represented by its concepts, and can hence be managed in a language-independent fashion. The research focus lies on the development and evaluation of methods for the Disambiguation of Named Entities. The representation of news documents as a set of concepts and concept relations then allows to search and group documents on the basis of these concepts, e.g. to create a press review.
|
-
Project: SERUM - Semantic Recommendations based on Large Unstructured Datasets
( Current )
SERUM establishes the basis for a semantic recommender system that calculates high quality recommendations based on a semantic analysis of user behavior and news articles. The aim of the project is to develop a recommender system that computes recommendations independently from a specific use case or domain. The recommendations are personalized and adapted to the specific needs of a user based on personal interests and preferences.
Within the SERUM research project, the goal is to recommend news articles based on the previous reading behavior of a user. This reading behavior is analyzed to create a personalized news digest for each user. The recommendation system is connected to a semantic knowledge base, which is modeled and managed as an ontology. The semantic knowledge is being linked with information from current news articles. Based on this semantic network, new algorithms were developed that analyze the semantic information and the user behavior to compute high quality recommendations.
|
-
Project: KMulE - Context-based Multimedia Recommender System
( Current )
Context-aware recommender systems are becoming a popular topic, yet there are still many untouched aspects. In this project, we study context identification and the concepts involved in hybrid and context-aware systems. The goal of the project is to implement a conceptual architecture for a context-aware recommender system for movies and TV shows. The system consists of a number of modules for context identification and recommendation. Key contextual features are identified and used for the creation of several sets of recommendations, based on the predicted context. The resulting prototype system will be evaluated and incorporated into the recommendation engine of movie and TV recommendation website Moviepilot.
|
-
Project: PIA – Personal Information Assistant
( Current )
The goal of the Personal Information Assistant project is to provide a comprehensive agent-based solution for the personalized and device-independent supply of information. The user receives information that is relevant to his personal needs and interests. This includes daily news, background knowledge on work issues, or information on leisure time plans and activities. Besides a typical web search engine interface, the PIA system allows users to define and save searches which are then continually monitored by search agents for any new developments. The architecture of the PIA system is designed to allow information sources to be flexibly integrated into the system. Information is analyzed and filtered using advanced filtering methods, e.g. content-based or collaborative filtering techniques. The use of multiple filtering techniques, which are guided by integrating user feedback from a learning and user modelling component, guarantees a high accuracy of search results.
|
-
Project: SPREE - A Community-Based Information Exchange Network
( Current )
The main focus of the SPREE project is the implementation of an online portal for an efficient knowledge transfer between its users. Therefore the platform has to be capable of identifying the best qualified users for answering a given query in real time, and the quality of the algorithm doing the matching between query and experts will be of central importance. Moreover the portal will provide means - such as chat - allowing users and experts to directly communicate with each other. The SPREE project provides an online portal offering the functionality of automatically identifying the best qualified users (experts) for a given query. Furthermore the system will offer means such as chat for a direct communication between user and expert in order to maximize the result quality.
|
-
Project: RDF-OWL EuroWordNet Representation
( 2007 - 2008 )
After a deep analysis of the different problems related to lexical resources and in particular to WordNet and its variations, I decided to convert EuroWordNet, the much richer multilingual WordNet variant, into an RDF/OWL representation. The decision of converting EuroWordNet was based on the need of extending it (because not all meanings are covered) with other resources. These resources are domain-specific and could enhance the coverage of meanings used for the semantic classification of the documents (as I discussed in my doctoral thesis). The novelty of this approach is to extend the monolingual WordNet RDF/OWL representation for a multilingual purpose, but also for a possible domain-specific extension, because most domain-specific ontologies are written in OWL.
Together with Aldo Gangemi (the Laboratory of applied ontologies in Rom, Italy), I am working on the possibility to integrate my multilingual RDF/OWL EuroWordNet representation into the standardized W3C RDF/OWL representation of WordNet.
Together with Birte Lönneker-Rodman (International Computer Science Institute der University of California, Berkeley), I am now exploring possibilities to convert the Hamburg Metaphor Database into my RDF/OWL Format.
|
-
Project: User Adaptive Interfaces
( 01.05.2003 - 30.04.2008 )
This project was part of European Network of Excellence on Intelligent Technologies for Smart Adaptive Systems (EUNITE) to review the state of the art in user adaptive search interfaces and to initiate and intensify research collaboration between different research communities and the industry. During the last years several approaches have been developed that tackle specific problems of the retrieval process, e.g. feature extraction methods for multimedia data, problem specific similarity measures and interactive user interfaces. These methods enable the design of efficient retrieval tools if the user is able to provide an appropriate query. However, in most cases the user needs several steps in order to find the searched objects. The main reasons for this are on the one hand, the problem of users to specify their interests in the form of a well defined query (which is partially caused by inappropriate user interfaces), on the other hand, the problem of extracting relevant features from the (multimedia) objects. To improve today’s retrieval tools and thus the overall satisfaction of a user, it is necessary to develop methods that are able to support the user in the search process, e.g. by providing additional information about the search results as well as the data collection itself and also by adapting the retrieval tool to the users needs and interests. I implemented different tools and applications.
|
-
Project: ELDIT (Elektronisches Lernerwörterbuch Deutsch-Italienisch)
( 2003 )
The ELDIT program (Electronic learners Dictionary German Italian) is an online platform for beginning to intermediate language learners. It is targeted at German native speakers that wish to learn Italian and Italian native speakers that wish to learn German. Currently ELDIT includes a learners' dictionary, a text corpus (texts of the so-called exams in bilingualism), a grammar module and interactive quizzes.
|
-
Project: PEACH
( 2002 )
PEACH is a project that addresses these and other questions that individuals around the world ask themselves every day when visiting a cultural institution. The project objective is that of studying and experimenting with advanced technologies that can enhance cultural heritage appreciation by creating an interactive and personalized guide. The aim is that of developing and using innovative technology to provide an educational and entertaining experience fit for each individual's background, needs and interests. PEACH is funded by the Autonomous Province of Trento under the Fondo Unico program. The two major partners are ITC-IRST and DFKI, with a number of other research institutions participating in the consortium.
|
-
Project: Renaissance
( 2001 )
Virtual Renaissance Court is a research and development project funded by the European Commission as part of the framework of the IST programme. The project is being directed by Italian electronic publisher Giunti Multimedia, and involves the German virtual community specialists, Blaxxun Interactive, the Swedish game publishers, Iridon Interactive, and the Italian research institute Istituto Trentino di Cultura (ITC-IRST). The aim of the Renaissance project is to develop a new genre of edutainment applications featuring a high quality graphical interface, networked co-operative environments, scientifically validated contents and an innovative pedagogical approach. This enables the reproduction of historically fascinating environments while using the appealing interface of a game in order to teach history. The project foresees the development of a prototype reproducing life in a Renaissance court, a 3D multi player Internet application where the users can play the role of different courtiers at the same court.
|
-
Project: M-Piro (Multilingual Personalized Information Objects)
( 2001 )
Multilingual information delivery via the web for museum settings with personalized descriptions of museum exhibits with six international partners. The M-PIRO software creates descriptions of museum artefacts automatically, using information stored in a database. Children, adults and experts all receive slightly different, personalised, descriptions. The system also remembers what viewers have looked at before in order to avoid repetition and to draw comparisons with previously seen objects. Currently the technology can generate text in English, Italian or Greek.
|
-
Tool: CARSA - A Context Adaptive Retrieval System Architecture
( 2005 - 2008 )
CARSA is a web services based architecture, which supports the development of context based information retrieval systems. The idea of these systems is to support users in the search process by, e.g., adapting the search results as well as the interface itself to user specific needs and interests. CARSA's data and program structure was designed based on web services and XML. This allows to easily integrate and combine different methods to search data locally or on the web (meta-searcher functionality), to modify or categorize search results, and to develop visualization methods on diverse clients (e.g. desktop PCs or mobile devices). In addition, CARSA contains a testing environment for evaluating single methods, e.g. classification or clustering methods, or their combinations with standard performance measures on benchmark data sets.
In the research group in Magdeburg, I contributed in designing and implementing the system architecture. Furthermore, I designed my own plug-ins for indexing, categorizing and visualizing information.
|
-
Tool: RDF/OWL LexiRes
( 2006 - 2008 )
I implemented the RDF/OWL LexiRes as a visualization tool for handling structures of ontological and lexical databases. The main idea of this tool is to give authors the possibility to navigate ontology hierarchies in order to restructure them, by manual or automatic merging, adding or deleting word senses. The tool is implemented in Java and uses the Jena Semantic Web Framework for querying and retrieving lexical data.
|
-
Tool: MultiLexExplorer
( 2006 - 2008 )
MultiLexExplorer is a tool that combines a knowledge-driven word sense disambiguation with a knowledge-based text retrieval approach in an interactive framework. Lexical resources are used in order to disambiguate documents (retrieved from the web or a local document collection) given the different meanings (retrieved from the lexical resources, in our case EuroWordNet) of a search term having unambiguous description in different languages. The focus is especially on the integration of methods that support the adaptation of the system interface and the output to the current search context. This tool has been a joint work with a student, who concluded then his diploma-thesis on this task.
|
-
Tool: Multilingual Sense Folder Interface
( 2003 - 2008 )
The Multilingual Sense Folder Interface is an interface for supporting users in an interactive semantic-based search process. Semantic classes created from lexical resources are used for this purpose and combined with word sense disambiguation, multilingual text retrieval and document categorization techniques. The focus is on the problem of browsing and navigating information and the related different word senses of a query for filtering only the relevant documents related to these meanings. Moreover, the user is supported by named-entity recognition, spell checking and stemming methods. These components have been integrated in the user interface. I implemented this interface as a part of my doctoral thesis.
|
| |
|
|