Anastasia Karanastasi

The OntoNL framework for natural language interface generation and a domain-specific application

We present in this paper the design and implementation of the OntoNL Framework, a natural language interface generator for knowledge repositories, as well as a natural language system for interactions with multimedia repositories which was built using the OntoNL Framework. The system allows the users to specify natural language requests about the multimedia content with rich semantics that result to digital content delivery. We propose and evaluate a semantic relatedness measure for OWL domain ontologies that concludes to the semantic ranking of ontological, grammatically-related structures. This procedure is used to disambiguate in a particular domain of context and represent in an ontology query language, natural language expressions. The ontology query language that we use is the SPARQL. The construction of the queries is automated and also dependent on the semantic relatedness measurement of ontology concepts. We also present the results of experimentation with the system.

Ontology-Driven Semantic Ranking for Natural Language Disambiguation in the OntoNL Framework

The measurement of the semantic relatedness has many applications in natural language processing, and many different measures have been proposed. Most of these measures use WordNet as their central resource and not domain ontologies of a particular context. We propose and evaluate a semantic relatedness measure for OWL domain ontologies that concludes to the semantic ranking of ontological, grammatically-related structures. This procedure is used to disambiguate in a particular domain of context and represent in an ontology query language, natural language expressions. The ontology query language that we use is the SPARQL. The construction of the queries is automated and also dependent on the semantic relatedness measurement of ontology concepts. The methodology has been successfully integrated into the OntoNL Framework, a natural language interface generator for knowledge repositories. The experimentations show a good performance in a number of OWL ontologies.

Semantic Processing of Natural Language Queries in the OntoNL Framework

The OntoNL Framework provides an architecture and re-usable components for automating as much as possible the building of natural language interfaces to information systems. In addition to the syntactic analysis components, OntoNL has semantic analysis components which exploit domain ontologies to provide better disambiguation of the user input. We present in this paper the algorithms used for semantic processing of the natural language queries, as well as an ontology-driven semantic relatedness measure developed for this purpose. We also present extensive evaluation results with different ontologies using human subjects.

Agent Technology Meets the Semantic Web: Interoperability and Communication Issues

This overview paper is a survey of recent research on agent technologies and how this technology can serve the scopes of the Semantic Web project. In a short time, Web has become the dominant database for information retrieval. Due to the exponential growth of the Web and the information it provides, finding accurate information is becoming more and more difficult. In the near future, access to Web will be mediated by intelligent applications and software agents that will assist users in finding accurate information and complete transactions successfully. Concisely, the Semantic Web means ontologies and semantics, software agents means multi-agents systems (MASs) built in FIPA 2002 and other agent platforms with their own standards, and Web services means XML. We will try to investigate the way these technologies can cooperate without changing their specifications.

A natural language model for managing TV-Anytime information in mobile environments

The TV-Anytime standard describes structures of categories of digital TV program metadata, as well as User Profile metadata for TV programs. We describe a natural language model for the users to interact with the TVAnytime metadata and preview TV programs from their mobile devices. The language utilizes completely the TV-Anytime metadata specifications and it can accommodate future metadata extensions. The interaction model does not use clarification dialogues, but it uses the user profiles to rank the possible answers in case of ambiguities, as well as TV-Anytime Metadata information and ontologies with information concerning digital TV. We describe an implementation of the language that runs on a PDA and a mobile phone and manages the metadata on a remote TV-Anytime compatible TV set.

A Natural Language Model and a System for Managing TV-Anytime Information from Mobile Devices

The TV-Anytime standard describes structures of categories of digital TV program metadata, as well as User Profile metadata for TV programs. In this case study we describe a natural language model and a system for the users to interact with the metadata and preview TV programs stored in remote databases, from their mobile devices contrary to their limited configurations. By the use of the TV-Anytime metadata specifications the system limits greatly the possibility for ambiguities. The interaction model deals with ambiguities by using the TV-Anytime user profiles and metadata information concerning digital TV to rank the possible answers. The interaction between the user and the system is done by the use of a PDA and a mobile phone with metadata information stored on a database on a remote TV-Anytime compatible TV set.