B.C.M. Wondergem, P. van Bommel, and Th.P. van der Weide. Matching Index Expressions for Information Retrieval. In: Information Retrieval Journal, Nr: 4, Vol: 2, 2000, To appear..
The INN system is a dynamic hypertext tool for searching and exploring the WWW. It uses a dynamically built ancillary layer to support easy interaction. This layer features the subexpressions of index expressions that are extracted from rendered documents. Currently, the INN system uses keyword based matching. The effectiveness of the INN system may be increased by using matching functions for index expressions. In the design of such functions, several constraints stemming from the INN must be taken into account. Important constraints are a limited response time and storage space, a focus on discriminating (dirent notions of) subexpressions for index expressions, and domain independency. With these contextual constraints in mind, several matching functions are designed and both theoretically and practically evaluated.
J.J. Sarbo, J.I. Farkas, F.A. Grootjen, P. van Bommel, and Th.P. van der Weide. Meaning Extraction from a Peircean Perspective. In: International Journal of Computing Anticipatory Systems, Vol: 6, Pages: 209-227, 2000.
Meaning extraction from text documents is a form of information management. The approach suggested in this paper is based on Peirce's semiotic which, by virtue of its deeper foundation, provides us with an adequate modelling of the information content of language. We exemplify the potential of the Peircean approach by extracting the meaning of a sample English text.
B.C.M. Wondergem. Compact and Tractable Descriptors for Information Discovery. University of Nijmegen, 2000, ISBN 906464831X.
[ Missing PDF ] [ Bibtex ]
A.T. Arampatzis, Th.P. van der Weide, C.H.A. Koster, and P. van Bommel. Linguistically-motivated Information Retrieval. Pages: 201-222, Marcel Dekker, New York, New York, USA, 2000.
This article discusses a retrieval schema that attempts to overcome the problems originat- ing from the keyword retrieval hypothesis and linguistic variation. After discussing some of the most important attempts made to deal with linguistic variation, followed by as sicussion of the key aspects of a linguistically motivated retrieval system. Starting from a phrase retrieval hypothesis - a naive extension of the keyword retrieval hypothesis - we will address a suitable for IR representation of phrases. Possible regularizations of natural language will be outlined. The weighting of phrasal indexing terms and their matching is discussed. An example architecture of such a linguistically motivated retrieval system is depicted.
F.C. Berger, P. van Bommel, and Th.P. van der Weide. Characterization hierarchy containing augmented characterizations. Pages: 1-21, Marcel Dekker, New York, New York, USA, 2000.
The focus of this paper is information retrieval and filtering in traditional retrieval contexts as well as on the Internet. Information Modelling techniques (e.g. NIAM, ER, OO) are used for the characterization of documents to be retrieved. This brings together the worlds of Information Modelling (IM) and Information Retrieval (IR, or: document retrieval). Although IM is in most cases used for traditional (non-document) databases such as relational databases (e.g. SQL), these techniques can be applied to IR in order to obtain different characterization levels for information objects.
The level of index expressions is discussed in detail and extended, yielding augmented index expressions containing additional (semantic) information. This is done in the following context. A searcher in a list of phrases serving as an index to documents often has problems finding the right words when the information sought for has to be described. Offering alternative phrasings and pointing to related concepts in the index could be a great help in this difficult process of query formulation.
Usually the index is obtained by characterizing documents. This paper describes the addition of semantic relations to the index. Various strategies for relating nodes in an index are discussed, and criteria for adding new index entries are introduced. The effects of adding relations on the process of offering support during the formulation process are treated as well.
Avi Arampatzis, Jean Beney, C. H. A. Koster, and Th.P. van der Weide. Incrementality, Half-Life, and Threshold Optimization, for Adaptive Document Filtering. In: The Nineth Text REtrieval Conference (TREC-9), Edited by: Ellen M. Voorhees, and Donna K. Harman. November 1, Department of Commerce, National Institute of Standards and Technology (NIST), Gaithersburg, Maryland, USA, 2000.
A.T. Arampatzis, Th.P. van der Weide, C.H.A. Koster, and P. van Bommel. An Evaluation of Linguistically-motivated Indexing Schemes. In: Proceedings of the 22nd BCS-IRSG Colloquium on IR Research, Pages: 34-45, April, 2000.
In this article, we describe a number of indexing experiments based on indexing terms other than simple keywords. These experiments were conducted as one step in validating a linguistically-motivated indexing model. The problem is important but not new. What is new in this approach is the variety of schemes evaluated. It is important since it should not only help to overcome the well-known problems of bag-of-words representations, but also the difficulties raised by non-linguistic text simplification techniques such as stemming, stop-word deletion, and term selection. Our approach in the selection of terms is based on part-of-speech tagging and shallow parsing. The indexing schemes evaluated vary from simple keywords to nouns, verbs, adverbs, adjectives, adjacent word-pairs, and head-modifier pairs. Our findings apply to Information Retrieval and most of related areas.
A.T. Arampatzis, Th.P. van der Weide, C.H.A. Koster, and P. van Bommel. Term Selection for Filtering based on Distribution of Terms over Time. In: Proceedings of the RIAO`2000 Conference, April, 2000.
In this article we investigate the use of time distributions in retrieval tasks. Specifically, we introduce a novel term selection method, namely Term Occurrence Uniformity (TOU), based on the hypothesis that terms which occur uniformly in time are more valuable than others. Our empirical evaluation so far has neither proved nor disproved this hypothesis. However, results are promising and suggest the need for a deeper theoretical and empirical investigation. Our current concern is filtering, but this line of research may easily be extended to other retrieval tasks which involve temporally-dependent data.
A.T. Arampatzis, J. Beney, C.H.A. Koster, and Th.P. van der Weide. Incrementality, Half-Life, and Threshold Optimization for Adaptive Document Filtering. In: Proceedings of the Nineth Text REtrieval Conference (TREC-9), November, Department of Commerce, National Institute of Standards and Technology (NIST)Gaithersburg, Maryland, USA, 2000.
[ Missing PDF ] [ Bibtex ]
J.I. Farkas, and J.J. Sarbo. A Logical Ontology. In: Working with Conceptual Structures: Contributions to ICCS2000, Edited by: G. Stumme. Pages: 138-151, Shaker-Verlag, Darmstadt, Germany, EU, 2000.
We make an attempt to develop a Peircean ontology that is presupposed by propositional logic. The result of this can be seen as a first step towards linking Peirce's semiotic to his logic of relatives. Familiarity with Peirce's semiotic can be useful, but the thesis of this paper is intelligible without such a background.
F.A. Grootjen. Employing semantical issues in syntactical navigation. In: Proceedings of the 22nd BCS-IRSG Colloquium on IR Research, Pages: 22-33, 2000.
Given their simple nature, the success of keyword based retrieval systems is astonishing. Although these methods seemingly only process words (and their word counts), they rely on and credit most of their success to the keyword's implicit semantics. In fact each keyword is a representation of a thought, or concept. Due to recent developments in NLP it is possible to use bigger syntactical units (like noun phrases) for IR purposes. Simply using these units as 'large keywords' drastically boosts precision, but due to their rare occurrences they really hurt recall. A way to deal with this problem is to add subphrases. The obtained phrases can be structured into a lithoid which forms an ideal starting point for feedback mechanisms like Query By Navigation. This paper will even go further and tries to involve the phrases' support into the structure using a mathematical theory called formal concept analysis. The resulting concept lattice shows great similarity to the original lithoid and, since it consists of formal concepts, leads the way to handle phrase semantics.
[ Missing PDF ] [ Bibtex ]
F.A. Grootjen. A Semantical Twist to Syntactical Navigation. In: Proceedings of the eleventh international workshop on Data Base and Expert Systems Applications, Greenwich, United Kingdom, EU, Edited by: P.D. Bruza, F. Crestani, and M. Lalmas. Pages: 523-528, IEEE, Los Alamitos, California, USA, 2000.
Given their simple nature, the success of keyword based retrieval systems is astonishing. Although these methods seemingly only process words (and their word counts), they rely on and credit most of their success to the keyword's implicit semantics. In fact each keyword is a representa-tion of a thought, or concept. Recent developments in NLP make it possible to use bigger syntactical units (like noun-phrases) for IR purposes. The obtained phrases (and their subphrases) can be structured into a lithoid which forms an ideal starting point for feedback mechanisms like 'Query By Navigation'. This paper will go even further and tries to involve the phrases' support into the structure using a mathematical theory called 'formal concept analysis'. The resulting concept lattice shows great similarity to the original lithoid and, since it consists of formal concepts, it leads the way to handle phrase semantics.
[ Missing PDF ] [ Bibtex ]
H.A. (Erik) Proper, H. Bosma, S.J.B.A. (Stijn) Hoppenbrouwers, and R.D.T. Janssen. An Alignment Perspective on Architecture-driven Information Systems Engineering. In: Proceedings of the Second National Architecture Congres, Edited by: D.B.B. Rijsenbrij. November, 2000.
This article provides a discussion on architecture-driven information systems engineering from a Business-IT alignment perspective. We do so by trying to develop a more fundamental understanding of the essence of Business-IT alignment. We try to find this understanding by viewing Business-IT alignment as the alignment between two co-evolving systems. An alignment that should take place at the strategic, the tactical as well as the operational level of these systems.
H.A. (Erik) Proper, H. Bosma, S.J.B.A. (Stijn) Hoppenbrouwers, and R.D.T. Janssen. Towards an Information Systems Engineering Body of Knowledge. In: Proceedings of the Second National Architecture Congres, Edited by: D.B.B. Rijsenbrij. November, 2000.
Though there may be millions of professionals worldwide acting as a designer, architect, or engineer in the design, realisation, and implementation of information systems, there is not yet a well established and clearly identified body of knowledge that can be said to define the profession. In this article, we present the idea of developing an information systems engineering body of knowledge. Such a body of knowledge could play a pivotal role in the further professionalisation of our discipline. The approach we take is an organic approach in which we first aim to gather a library with significant knowledge, demarcating the field, and then move on to integrate this into a consistent body of knowledge.
We also realise that this effort can not be done in isolation. This article should therefore also be regarded as an invitation for additional participants.
A. Stam, and H.A. (Erik) Proper. Improving Architectures by Simulation and Animation. In: Proceedings of the Second National Architecture Congres, Edited by: D.B.B. Rijsenbrij. November, 2000.
In this paper we present our ideas about using simulation and animation techniques to improve the understanding and the quality of architectures. We discuss the meaning of validation and verification for architectures and the value of simulation and animation in this context. We give an outline of what is needed in order to simulate systems based on their architecture and what can be accomplished by doing so. A small example is given to illustrate our ideas.
B.C.M. Wondergem, M. van Uden, P. van Bommel, and Th.P. van der Weide. INdex Navigator for Searching and Exploring the WWW. In: Proceedings of the Conferentie Informatiewetenschap (CIW`2000), April, 2000.
Searching information from a large and dynamic information space causes several problems, concerning, for instance, dynamic and vague information needs, too broad queries, and correctness and sensibility of descriptors. These problems may be attacked by navigational query The INN is a dynamic electronic service system for the WWW.
J.G. Beney, N. Gietema, and C.H.A. Koster. Strength Normalisation and Weight Initialisation for Winnow Algorithm. Technical report, University of Nijmegen, 2000, To appear..
[ Missing PDF ] [ Bibtex ]
E.-J. Elferich, H.A. (Erik) Proper, and A.P. de Vries. KennisIntegratie onder Architectuur. In: ID Nieuws, Vol: 6, Pages: 10-12, March, 2000, In Dutch.
In veel organisaties speelt kennis tegenwoordig een steeds belangrijkere rol. Bedrijfsprocessen worden steeds kennisintensiever. Dit betekent dat het voor de uitvoerenden van deze processen belangrijker wordt dat zij op het juiste moment over de juiste kennis beschikken. Het begrip kenniswerker staat voor al die werknemers die kennis toepassen, aanleveren of managen. Er zijn dus meerdere soorten kenniswerkers te onderscheiden, respectievelijk de kennisgebruikers, kennisleveranciers en kennismanagers.
Voor de IT-wereld is de uitdaging natuurlijk om applicaties te ontwikkelen die kenniswerkers kunnen ondersteunen bij het toepassen, aanleveren en managen van kennis ten behoeve van hun werkzaamheden.