Gordan Gledec

Advantages of online spellchecking: a Croatian example

Online spellchecking is commonly regarded as an auxiliary way of performing spellchecking. However, it offers a unique opportunity to constantly improve spellchecker linguistic functionality through interaction with the community of spellchecker users. Such a possibility is crucial for spellchecking in non‐central and under‐resourced languages, in order to overcome gaps in NLP tools between them and central languages. The paper describes Hascheck, a Croatian online spellchecker able to learn words from texts it receives. It started as the first Croatian spellchecker, hence as a basic NLP tool for an under‐resourced language, but due to its learning ability it demonstrates linguistic functionality comparable to that of conventional central‐language spellcheckers. Based on these experiences we also discuss the future of online spellchecking in the context of global NLP tasks. Copyright

Improving search on WWW.HR web directory by introducing ontologies

In this paper we propose ontology-based improvement of the Croatian Web directory search mechanism, which is currently not capable of executing queries that take into account the structure and semantics of users query. The proposed approach is verified by introducing an ontology in the domain (directory category) of “tourism”. We address three problems related to the search mechanism: low recall, high recall and low precision and vocabulary mismatch. The results show significant improvements in terms of subjective relevance and quality of results.

An economic approach to big data in a minority language

Googles n-gram project brought recently big data benefits to several main world languages, like English, Chinese etc. Any attempt to derive such systems, aimed to accelerate the development of NLP applications for world minority languages, in the manner in which it has been done in the project, encounters many obstacles. This paper presents an innovative and economic approach to large-scale n-gram system creation applied to the Croatian language case. Instead of using the Web as the worlds biggest text repository, our process of n-gram collection relies on the Croatian academic online spellchecker Hascheck, a language service publicly available since 1993 and popular worldwide. The service has already processed a corpus whose size exceeds the size of the Croatian web-corpus created in recent years. Contrary to the Google n-gram systems, where cutoff criteria were applied, our n-gram filtering is based on dictionary criteria. This resulted in a system comparable in size to the largest n-gram systems of today. Because of the reliance on a service in constant use, the Croatian n-gram system is a dynamic one, unique among the systems compared. The importance of having an n-gram infrastructure for rapid breakthroughs in new application areas is also exemplified in the paper.

Assessing Semantic Quality of Web Directory Structure

The administration of a Web directory content and associated structure is a labor intensive task performed by human domain experts. Because of that there always exists a realistic risk of the structure becoming unbalanced, uneven and difficult to use to all except for a few users proficient in a particular Web directory. These problems emphasize the importance of generic and objective measures of Web directories structure quality. In this paper we demonstrate how to formally merge Web directories into the Semantic Web vision. We introduce a set of objective criterions for evaluation of a Web directorys structure quality. Some criteria functions are based on heuristics while others require the application of ontologies.

An application for multidimensional analysis of the Web site traffic

Considers the use of online analytical processing (OLAP) tools to provide fast, interactive analysis of Web-site traffic. For the purpose of analysing our own hierarchically organized Web site, the Directory of Croatian WWW Servers, an OLAP application (OLAWEB) has been developed. We describe data extraction from existing server access log files, the data transformation necessary to prepare data for multidimensional analysis, and the storage of the Web-site traffic data. The basic characteristics of the OLAWEB application are explained. Using this application, the Web-site administrator and other users are able to get fast answers to many unpredictable and complex questions that could not be answered by available statistical tools.

Balancing Web server workload using genetic algorithms

The paper deals with a genetic algorithm for scheduling requests onto distributed Web servers with replicated content. This approach uses DNS as a mapping mechanism that enables a single structure URL view from a users perspective. Novel genetic algorithm DNS (GA-DNS) scheduling policy is proposed. An implementation of the proposed algorithm can be used in a cluster environment with a constant monitoring of the Web server performance.

Labeling and retrieval of emotionally-annotated images using WordNet

Repositories of images with semantic and emotion content descriptions are valuable tools in many areas such as Affective Computing and Human-Computer Interaction, but they are also important in the development of multimodal searchable online databases. Ever growing number of image documents available on the Internet continuously motivates research of better annotation models and more efficient retrieval methods which use mash-up of available data on semantics, scenes, objects, events, context and emotion. Formal knowledge representation of such high-level semantics requires rich, explicit, human but also machine-processable information. To achieve these goals we present an online ontology-based image annotation tool WNtags and demonstrate its usefulness in knowledge representation and image retrieval using the International Affective Picture System database. The WNtags uses WordNet as image tagging glossary but considers Suggested Upper Merged Ontology as the preferred upper labeling formalism. The retrieval is performed using node distance metrics to establish semantic relatedness between a query and the collaboratively weighted tags describing high-level image semantics, after which the result is ranked according to the derived importance. We also elaborate plans to improve the WNtags to create a collaborative Web-based multimedia repository for research in human emotion and attention.

Architecture of Hascheck: an intelligent spellchecker for croatian language

The design and development of a spellchecker for highly inflected languages is commonly regarded as a challenging task. In this paper we present the architecture of Hascheck, a spellchecking system developed for Croatian language. We describe functional elements that make it an intelligent system and discuss specific issues related to Haschecks dictionary size as well as its guessing and learning capabilities.