Abstract. Domain ontologies very rarely model verbs as relations holding between concepts. However, the role of the verb as a central connecting element between concepts is undeniable. Verbs specify the interaction between the participants of some action or event by expressing relations between them. In parallel, it can be argued from an ontology engineering point of view that verbs express a relation between two classes that specify domain and range. The work described here is concerned with relation extraction for ontology extension along these lines. We describe a system (RelExt) that is capable of automatically identifying highly relevant triples (pairs of concepts connected by a relation) over concepts from an existing ontology. RelExt works by extracting relevant verbs and their grammatical arguments (i.e. terms) from a domain-specific text collection and computing corresponding relations through a combination of linguistic and statistical processing. The paper includes a detailed description of the system architecture and evaluation results on a constructed benchmark. RelExt has been developed in the context of the SmartWeb project, which aims at providing intelligent information services via mobile broadband devices on the FIFA World Cup that will be hosted in Germany in 2006. Such services include location based navigational information as well as question answering in the football domain. 1

Abstract. Ontologies in current computer science parlance are computer based resources that represent shared conceptualizations for a specific domain. This paper first introduces ontologies in general and subsequently, in particular, shortly outlines the DOGMA ontology leaning approach. The paper also introduces the reader in the field of Knowledge Discovery in Text before, in the main part, work in progress is described and experimentally evaluated. It concerns a potential method to automatically extract concepts and conceptual relationships from texts. Preliminary outcomes are presented based on the clustering of nominal terms and prepositional phrases according to co-occurrence frequencies in the verb-object syntactic context. 1

Abstract. The main contribution of this paper is an initial method for automatically exploiting ontology design patterns with the aim of further automating the creation of enterprise ontologies in small-scale application contexts. The focus is so far on developing a fully automated construction method, thereby somewhat reducing the requirements on ontology customization and level of detail. In this paper we present an approach how to use knowledge (patterns) from other areas, like data modeling, knowledge reuse, software analysis and software design, to create ontology patterns. These design patterns are then used within our method for automatically matching and pruning them, in accordance with information extracted from existing knowledge sources within the company in question. Though the method still needs some fine-tuning, it has already been used when creating an enterprise ontology for a suppliercompany within the automotive industry. 1

In recent years there have been some efforts to automate the ontology acquisition and construction process. The proposed systems differ from each other in some distinguishing factors and have many features in common. This paper presents the state of the art in ontology learning (OL) and introduces a framework for classifying and comparing OL systems. The dimensions of the framework answer to questions about what to learn, from where to learn and how to learn. They include features of the input, the methods of learning and knowledge acquisition, the elements learned, the resulted ontology and also the evaluation process. To extract the framework over 50 OL systems or modules from the recent workshops, conferences and published journals are studied and seven prominent of them with most differences are selected to be compared according to our framework. In this paper after a brief description of the seven selected systems we will describe the framework dimensions. Then we will place the representative ontology learning systems into our framework. At last we will describe the differences, strengths and weaknesses of various values for our dimensions in order to present a guideline for researchers to choose the appropriate features (dimensions ’ values) to create or use an OL system for their own domain or application.

Abstract not found

Abstract. We report on an a set of experiments carried out in the context of the Flemish OntoBasis project. Our purpose is to extract semantic relations from text corpora in an unsupervised way and use the output as preprocessed material for the construction of ontologies from scratch. The experiments are evaluated in a quantitative and ”impressionistic ” manner. We have worked on two corpora: a 13M words corpus composed of Medline abstracts related to proteins (SwissProt), and a small legal corpus (EU VAT directive) consisting of 43K words. Using a shallow parser, we select functional relations from the syntactic structure subject-verb-direct-object. Those functional relations correspond to what is a called a ”lexon”. The selection is done using prepositional structures and statistical measures in order to select the most relevant lexons. Therefore, the paper stresses the filtering carried out in order to discard automatically all irrelevant structures. Domain experts have evaluated the precision of the outcomes on the SwissProt corpus. The global precision has been rated 55%, with a precision of 42 % for the functional relations or lexons, and a precision of 76 % for the prepositional relations. For the VAT corpus, a knowledge engineer has judged that the outcomes are useful to support and can speed up his modelling task. In addition, a quantitative scoring method (coverage and accuracy measures resulting in a 52.38 % and 47.12 % score respectively) has been applied.

Ontology generation and population is a crucial part of knowledge base construction and maintenance that enables us to relate text to ontologies, providing a rich and customised ontology related to the data and domain with which we are concerned. SPRAT combines aspects from traditional named entity recognition, ontology-based information extraction and relation extraction, in order to identify patterns for the extraction of a variety of entity types and relations between them, and to re-engineer them into concepts and instances in an ontology. When augmented with richer knowledge such as WordNet semantic categories and terminological information, the results are greatly improved. SPRAT can either modify an existing ontology or create a new ontology from scratch, which is specific to the corpus of texts processed. Preliminary results are very promising, although more refinement of the patterns is still necessary.

We present an approach for extracting relations from texts that exploits linguistic and empirical strategies, by means of a pipeline method involving a parser, partof-speech tagger, named entity recognition system, pattern-based classification and word sense disambiguation models, and resources such as ontology, knowledge base and lexical databases. The relations extracted can be used for various tasks, including semantic web annotation and ontology learning. We suggest that the use of knowledge intensive strategies to process the input text and corpusbased techniques to deal with unpredicted cases and ambiguity problems allows to accurately discover the relevant relations between pairs of entities in that text. 1

Abstract. In this paper, we present a weakly-supervised, general-purpose algorithm for IS-A relation extraction. The algorithm automatically identifies highly relevant triples for IS-A relation from a text collection and rank the triples through a combination of linguistic and statistical processing. The main features are: i) a method based on dependency structure analysis of texts, ii) a method to exploit domain knowledge based on distributional association of entities, and iii) a iterative and interactive measure of pattern and relation instance reliability. Experimental results show that the algorithm presented here has ranked patterns and instances in some ways preferable. As our approach is not dependent to IS-A relation, we can expand to the extraction of other relation types. Keywords: IS-A relation, relation extraction, domain knowledge, linguistic analysis, iterative weighting 1

• A hybrid approach for extracting semantic relations from texts. 2nd Workshop on Ontology