Vangelis Karkaletsis

Ontology population and enrichment: state of the art

Ontology learning is the process of acquiring (constructing or integrating) an ontology (semi-) automatically. Being a knowledge acquisition task, it is a complex activity, which becomes even more complex in the context of the BOEMIE project1, due to the management of multimedia resources and the multi-modal semantic interpretation that they require. The purpose of this chapter is to present a survey of the most relevant methods, techniques and tools used for the task of ontology learning. Adopting a practical perspective, an overview of the main activities involved in ontology learning is presented. This breakdown of the learning process is used as a basis for the comparative analysis of existing tools and approaches. The comparison is done along dimensions that emphasize the particular interests of the BOEMIE project. In this context, ontology learning in BOEMIE is treated and compared to the state of the art, explaining how BOEMIE addresses problems observed in existing systems and contributes to issues that are not frequently considered by existing approaches.

Named Entity Recognition from Greek Texts: The GIE Project

Todays’ overload of information, particularly through the World Wide Web, makes difficult the users’ access to the right information. The situation becomes even more difficult due to the fact that a lot of this information is in different languages. Therefore, it is important to apply an information process that will extract from all that volume of information only the facts that match users’ interests, and allow the user to access facts written in a different language. Information Extraction (IE) technology can meet these requirements, since unlike what happens with information retrieval and filtering technology, in IE the user interests are on specific facts extracted from the documents and not on the documents themselves. Some documents may contain the requested keywords but be irrelevant to the users’ interests. Working with specific facts instead of documents provides users information more relevant to their domain of interest. The IE systems developed so far, extract, in most cases, fixed information from documents in a fixed language. However, in order for the IE technology to be truly applicable in real life applications, meeting the above requirements, IE systems need to be easily adaptable (customisable) to new domains and users interests, as well as to multiple languages. During the last decade, substantial progress has been made in developing reliable Information Extraction (IE) technology. IE technology is currently exploited in real applications, such as the extraction of information for companies acquisitions [1],[2],[3], stock exchanges [4], companies profits and losses [5], joint ventures and management succession events [6],[7],[8], as well as for the understanding of military messages [9] and police reports [10],[11],[12].

Integrating User Modeling Into Information Extraction: The UMIE Prototype

This paper introduces user modeling into the process of information extraction. It presents the user modeling prototype (UMIE) that we developed during the research project ECRAN. UMIE takes as input information extracted from corpora and adapts it according to the user’s interests in domain categories.

Authoring Semantic and Linguistic Knowledge for the Dynamic Generation of Personalized Descriptions

We present the ELEON/NATURALOWL system, an application of Semantic Web and Natural Language Generation technologies that combines a conceptual representation of cultural heritage objects with linguistic and adaptation resources. This combined model is used to automatically generate multi-lingual and personalized textual descriptions of cultural heritage objects represented as instances of an OWL domain ontology annotated by RDF linguistic and adaptation resources. Metadata and annotations are created using an authoring environment, which considerably reduces the effort required to port the system to a new domain.

The Use of Terminological Knowledge Bases in Software Localization

This paper describes the work that was undertaken in the Glossasoft 1 project in the area of terminology management. Some of the drawbacks of existing terminology management systems are outlined and an alternative approach to maintaining terminological data is proposed. The approach which we advocate relies on knowledge-based representation techniques. These are used to model conceptual knowledge about the terms included in the database, general knowledge about the subject domain, application-specific knowledge, and — of course — language-specific terminological knowledge. We consider the multifunctionality of the proposed architecture to be one of its major advantages. To illustrate this, we outline how the knowledge representation scheme, which we suggest, could be drawn upon in message generation and machine-assisted translation.

Symbolic and Neural Learning of Named-Entity Recognition and Classification Systems in Two Languages

This work compares two alternative approaches to the problem of acquiring named-entity recognition and classification systems from training corpora, in two different languages. The process of named-entity recognition and classification is an important subtask in most language engineering applications, in particular information extraction, where different types of named entity are associated with specific roles in events. The manual construction of rules for the recognition of named entities is a tedious and time-consuming task. For this reason, effective methods to acquire such systems automatically from data are very desirable. In this paper we compare two popular learning methods on this task: a decision-tree induction method and a multi-layered feed-forward neural network. Particular emphasis is paid on the selection of the appropriate data representation for each method and the extraction of training examples from unstructured textual data. We compare the performance of the two methods on large corpora of English and Greek texts and present the results. In addition to the good performance of both methods, one very interesting result is the fact that a simple representation of the data, which ignores the order of the words within a named entity, leads to improved results over a more complex approach that preserves word order.

A System of Recognition Services for Clinical Assessment

As smart interconnected sensing devices are becoming increasingly ubiquitous, more applications are becoming possible by re-arranging and re-connecting sensing and sensor signal analysis in different pipelines. Naturally, this is best facilitated by extremely thin services that expose minimal functionality and are extremely flexible regarding the ways in which they can be re-arranged. On the other hand, this ability to reuse might be purely theoretical since there are established patterns in the ways processing pipelines are assembled. By adding privacy and technical requirements, the re-usability of some functionalities is further restricted, making it even harder to justify the communication and security overheads of maintaining them as independent services. This creates a design space that each application must explore using its own requirements. In this article, we focus on detecting Activities of Daily Life (ADL) for medical applications and especially independent living applications, but our setting also offers itself to sharing devices with home automation and home security applications. By studying the methods and pipelines that dominate the audio and visual analysis literature, we observe that there are several multicomponent subsystems that can be encapsulated by a single service without substantial loss of re-usability. We then use this observation to propose a design for our ADL recognition application that satisfies our medical and privacy requirements, makes efficient use of processing and transmission resources and is also consistent with home automation and home security extensions.

Design for a System of Multimodal Interconnected ADL Recognition Services

As smart interconnected sensing devices are becoming increasingly ubiquitous, more applications are becoming possible by re-arranging and re-connecting sensing and sensor signal analysis in different pipelines. Naturally, this is best facilitated by extremely thin services that expose minimal functionality and are extremely flexible regarding the ways in which they can be re-arranged. On the other hand, this ability to re-use might be purely theoretical since there are established patterns in the ways processing pipelines are assembled. By adding privacy and technical requirements the re-usability of some functionalities is further restricted, making it even harder to justify the communication and security overheads of maintaining them as independent services. This creates a design space that each application must explore using its own requirements. In this article we focus on detecting activities of daily life (ADL) for medical applications and especially independent living applications, but our setting also offers itself to sharing devices with home automation and home security applications. By studying the methods and pipelines that dominate the audio and visual analysis literature, we observe that there are several multi-component sub-systems that can be encapsulated by a single service without substantial loss of re-usability. We then use this observation to propose a design for our ADL recognition application that satisfies our medical and privacy requirements, makes efficient use of processing and transmission resources, and is also consistent with home automation and home security extensions.

An Open Platform for Collecting Domain Specific Web Pages and Extracting Information from Them

The paper presents a platform that facilitates the use of tools for collecting domain specific web pages as well as for extracting information from them. It also supports the configuration of such tools to new domains and languages. The platform provides a user friendly interface through which the user can specify the domain specific resources (ontology, lexica, corpora for the training and testing of the tools), train the collection and extraction tools using these resources, and test the tools with various configurations. The platform design is based on the methodology proposed for web information retrieval and extraction in the context of the R&D project CROSSMARC.