Nikitas N. Karanikolas

A parametric methodology for text classification

Finding the correct category (class) a new unclassified document belongs to is an interesting and difficult problem, with a wide range of applications. Our methodology for narrative text classification is based on two techniques: we calculate the distance (similarity) between the new unclassified document and all the pre-classified documents of each class and also calculate the similarity of the new document to the ‘average class document’ of each class. In both cases we use key phrases (text phrases or key terms) as the distinctive features of our text classification methodology and eventually the proposed text classification method is based on the automatic extraction of an authority list of key phrases that is appropriate for discriminating between different classes. In this paper, we apply this methodology in handling Greek text and we present the key concepts, the algorithms, and some critical decisions. A number of parameters of the mining algorithm are also fine tuned. The actual text classification system, the adopted (embedded) ideas and the alternative values of parameters are evaluated using two training sets (test collections).

Computer assisted information resources navigation

In this paper, the design and development of Computer Assisted Information Resources Navigation (CAIRN) is discussed. CAIRN system is a medical information retrieval system that allows physicians and students to store full text medical information from any resource, organize and retrieve it. The most important feature of CAIRN is its capability to assist the user, physician, student etc. in selecting documents against a submitted query in Natural Language. The retrieved documents are presented in decreasing order according to their similarity to the submitted query. The nearest neighbour method is used. An alternative similarity measure based on a new calculation of the length of documents is proposed and some experimentation with it is discussed.

Bootstrapping the Albanian Information Retrieval

In this paper we investigate the Albanian language and try to uncover the characteristics of the language that will permit the Information Retrieval (IR) community to develop IR systems adapted for the specific language. As a consequence of our study (investigation) we provide a naive-single-step (rudimentary) stemming algorithm for the Albanian language. A stopword list is also created. Human experts are contacted for the evaluation of the provided stemming algorithm. The evaluation method used and the observation of the method’s results uncover more rules, which could improve the capabilities of the rudimentary stemming algorithm. We believe that our approach for this specific language could become a standard way for building Information Retrieval functionalities (tools, functions, etc) for languages less perused, as is the language studied in this paper.

Naive Rule Induction For Text ClassificationBased On Key-phrases

In this paper, we focus on the induction of naive rules for classifying text documents. An algorithm is briefly described for the creation of key-phrases from a given set of documents and these key-phrases are organized and used as features for the automatic classification of new documents. An Authority list of key-phrases is specified by the algorithm containing key-phrases that are frequent within the documents of only one or few classes in the training set. In this framework, this last property permitted us the creation of naive rules that measure the similarity of new documents with the existing classes.

A methodology for building simple but robust stemmers without language knowledge: overview, data model and ranking algorithm

The purpose of this work is to define a methodology for building simple but robust stemmers, without having knowledge of the stemmers target language. The target stemmer is based on conditional suffix replacement (actually suffix removal) in one or more steps. The building process (that refines the stemmer) uses the arguments of experts against the results of a primary stemmer. Even the experts did not need be speakers of the target language. They have available the original words, their translations (in their native language) and the results (stems) produced by the primary stemmer. The language resources are only a list of suffixes (used in the target language) and the translations of the terms existing in a corpus of texts from the target language.

Personal digital libraries: a self-archiving approach

Purpose – The purpose of this paper is to examine personal digital libraries (PDL) as a self-archiving approach, mainly based on individuals’ activities. Literature presents a wide range of perceptions of the term PDL. The rationale of using PDL and the capabilities that PDL should offer are also discussed. The key questions we focus on are: “What are the critical features of PDL?” and “Are there technologies that enable the implementation/incorporation of such capabilities in a low cost software product?” Design/methodology/approach – We focus on “a user centred view of information process”, and examine how PDL could assist individuals to “create, seek, share and manage the life of information” (Foster et al., 2010). The capabilities that PDL should support, and the related technologies, are also discussed. Then, we describe experimentation with a prototype implemented to support/provide the mentioned capabilities. It is used to clarify our view for the creation of PDL. Finally, further discussion and co...

Structuring a Multimedia Tri-Dialectal Dictionary

This paper deals with the problem of designing and implementing a multimedia electronic dictionary of three Greek dialects in Asia Minor (Pontic, Cappadocian, Aivaliot). At first, we present the linguistic and lexicographic approach adopted, as well as the principles for designing the macro/microstructure of the dictionary. Next, we present and describe the conceptual model of the tri-dialectal dictionary. Finally, we discuss the relational schema and implementation issues. Although, in its current state, the system hosts three dialects, it is designed so as to be able to incorporate other dialectal dictionaries in the future.

CUDL language semantics: Updating FDB data

The semantics for data manipulation of the database language CUDL - Conceptual Universal Database Language - designed to manage dynamic database environments, are presented. This language conforms to the FDB (Frame DataBase) data model, offering a simple, easy and efficient platform for the use of the FDB model. Otherwise the management and operation of FDB data is laborious and time-consuming and it requires from the user a very good acquaintance of the proposed model, the structures and organisation of it as well as the processes of the management of elements that compose it. In this paper we present in depth the semantics of the way of handling the data, in order to search and transform information, in an FDB data source. We present the analysis of simple and complex cases that led us to synthesize valid and simple semantic rules that determine the data manipulation operations. The more sophisticated and demanding constructs, used in the language, for query specification, query processing and object manipulation are discussed and evaluated.

Supervised learning for building stemmers

This work is part of a project aiming to define a methodology for building simple but robust stemmers, having primitive knowledge of the stemmer’s target language. The methodology starts with a very simple primary stemmer that simply removes the longest suffix (using the primitive knowledge – the list of available suffixes) that matches the ending of the examined word. Information retrieval (IR) experts express their arguments against the results of the primary stemmer. These (the experts’ arguments) are valuable knowledge that offer us the ability to apply supervised learning in order to automatically produce better stemmers (that conform to the arguments expressed by the IR experts). We also conduct an evaluation of our supervised learning-based methodology that builds stemmers for languages that the experts do not have knowledge on.

Towards a Unified Exploitation of Electronic Dialectal Corpora: Problems and Perspectives

In this paper, we deal with the problem of storing and retrieving dialectal data in a unified framework. In particular, we discuss issues concerning the design and implementation of a multimedia database which will contain written and oral data from three Greek dialects in Asia Minor. At first, we describe the overall architecture of a system aiming at providing the user with the possibility to store audio recordings, text transcripts, and other annotations. Then we discuss the possibilities and limitations of a retrieval module aiming at combining different linguistic levels for a unified exploitation of oral and written corpora.