Non-taxonomic relations between concepts appear as a major building block in common ontology definitions. In fact, their definition consumes much of the time needed for engineering an ontology. We here describe

Ontologies have become an important means for structuring information and information systems and, hence, important in knowledge as well as in software engineering. However, there remains the problem of engineering large and adequate ontologies within short time frames in order to keep costs low. For this purpose, eorts have been made to facilitate the ontology engineering process, in particular the acquisition of ontologies from domain texts. We present a general architecture for discovering conceptual structures and engineering ontologies. Based on the architecture we propose a new approach to extend current approaches, who mostly focus on the semi-automatic acquisition of taxonomies, by the discovery of non-taxonomic conceptual relations. We use a generalized association rule algorithm that does not only detect relations between concepts, but also determines the appropriate level of abstraction at which to dene relations. 1 Introduction Ontologies 1 have shown their usefulness...

This paper describes our actual and ongoing work in supporting semi-automatic ontology acquisition from a corporate intranet of an insurance company. A comprehensive architecture and a system for semi-automatic ontology acquisition supports processing semi-structured information (e.g. contained in dictionaries) and natural language documents and including existing core ontologies (e.g. GermaNet, WordNet). We present a method for acquir- ing a application-tailored domain ontology from given heterogeneous intranet sources.

Traditional information retrieval typically represents data using a bag of words; data mining typically uses a highly structured database representation. This paper explores the middle ground using a representation which we term entity models, in which questions about structured data may be posed and answered, but the complexities and task-specific restrictions of ontologies are avoided. An entity model is a language model or word distribution associated with an entity, such as a person, place or organization. Using these perentity language models, entities may be clustered, links may be detected or described with a short summary, entities may be collectively classified, and question answering may be performed. On a corpus of entities extracted from newswire and the Web, we group entities by profession with 90 % accuracy, improve accuracy further on the task of classifying politicians as liberal or conservative using collective classification and conditional random fields, and answer questions about “who a person is ” with mean reciprocal rank (MRR) of 0.52. 1.

This paper illustrated the application of cooccurrence theory to generate lightweight ontologies semi-automatically. First, the relationship of Information Retrieval (IR) and Artificial Intelligence (AI) is discussed in a general way. Then two case studies have been conducted to generate lightweight ontologies in specific domains (Information Retrieval domain and European part of CIA FactBook). Further discussion was articulated and future work was proposed, especially the possible future research direction on ontology learning. 1.

Non-taxonomic relations between concepts appear as a major building block in common ontology definitions. In fact, their definition consumes much of the time needed for engineering an ontology. We here describe a new approach for mining nontaxonomic conceptual relations from text building on shallow text processing techniques. We use a generalized association rule algorithm that does not only detect relations between concepts, but also determines the appropriate level of abstraction at which to define relations. This is crucial for an appropriate ontology definition in order that it be succinct and conceptually adequate and, hence, easy to understand, maintain, and extend. We also perform an empirical evaluation of our approach with regard to a manually engineered ontology. For this purpose, we present a new paradigm suited to evaluate the degree to which relations that are learned match relations in a manually engineered ontology.

Abstract. The discovery of non-taxonomical relationships is one of the less studied knowledge acquisition tasks, even though it is a crucial point in ontology learning. We present an automatic and unsupervised methodology for extracting non-taxonomically related concepts and labelling relationships, using the whole Web as learning corpus. We also discuss how the obtained relationships may be automatically evaluated, using relatedness measures based on WordNet. 1

. Applying knowledge acquisition from text supporting the ontology engineering task seems promising. Among all knowledge sources, texts are the most important source of knowledge for any kind of application, as they usually contain shared and stabilized knowledge among a community of specialists. Several algorithms, frameworks and tools have been proposed supporting ontology acquisition from text. However, there are no formal methods, which support comparing and evaluating the results concerning acquired conceptual structures from text. In this paper, we present a new mulit-level approach for cross-comparing ontologies and the corresponding algorithms. As comparing the accuracy of techniques for learning ontologies is not a trivial task, we do nut measure correctnes, but the degree of coincidence of acquired conceptual structures based on semantic similarity. 1 Introduction Ontologies have been widely applied in AI to facilitate knowledge sharing and reuse. The WWW opens new applicati...

We propose entity language models, a probabilistic representation of the language used to describe a named entity (person, organization, or location). The model is purely statistical and constructed from snippets of text surrounding mentions of an entity. We evaluate the effectiveness of entity models in three tasks: fact-based question answering, classification into pre-defined groups, and description of the relationship between two entities. The results on all tasks are promising.