Ontology Population Research Articles

Integration Languages for Data-Driven Approaches to Ontology Population and Maintenance

Populating an ontology with a vast amount of data and ensuring the quality of the integration process by means of human supervision seem to be mutually exclusive goals that nevertheless arise as requirements when building practical applications. In our case, we were confronted with the practical problem of populating the EFGT Net, a large-scale ontology that enables thematic reasoning in dierent NLP applications, out of already existing and partly very large data sources, but on condition of not putting the quality of the resource at risk. We present here our particular solution to this problem, which combines, in a single tool, on one hand an integration language capable of generating new entries for the ontology out of structured data with, on the other hand, a visualization of conflicting generated entries with online ontology editing facilities. This approach appears to enable ecient human supervision of the population process in an interactive way and to be also useful for maintenance tasks.

A redundancy-based method for the extraction of relation instances from the Web

The Semantic Web requires automatic ontology population methods. We developed an approach, that given existing ontologies, extracts instances of ontology relations, a specific subtask of ontology population. We use generic, domain-independent techniques to extract candidate relation instances from the Web and exploit the redundancy of information on the Web to compensate for loss of precision caused by the use of these generic methods. The candidate relation instances are then ranked based on co-occurrence with a small seed set. In an experiment, we extracted instances of the relation between artists and art styles. The results were manually evaluated against selected art resources. The method was also tested in the football domain. We also compare the performance of our ranking to that of a Google-hit count-based method.

Transforming arbitrary tables into logical form with TARTAR

The tremendous success of the World Wide Web is countervailed by efforts needed to search and find relevant information. For tabular structures embedded in HTML documents, typical keyword or link-analysis based search fails. The Semantic Web relies on annotating resources such as documents by means of ontologies and aims to overcome the bottleneck of finding relevant information. Turning the current Web into a Semantic Web requires automatic approaches for annotation since manual approaches will not scale in general. Most efforts have been devoted to automatic generation of ontologies from text, but with quite limited success. However, tabular structures require additional efforts, mainly because understanding of table contents requires the comprehension of the logical structure of the table on the one hand, as well as its semantic interpretation on the other. The focus of this paper is on the automatic transformation and generation of semantic (F-Logic) frames from table-like structures. The presented work consists of a methodology, an accompanying implementation (called TARTAR) and a thorough evaluation. It is based on a grounded cognitive table model which is stepwise instantiated by the methodology. A typical application scenario is the automatic population of ontologies to enable query answering over arbitrary tables (e.g. HTML tables).

Constructing and maintaining knowledge organization tools: a symbolic approach

Purpose - To propose a comprehensive and semi-automatic method for constructing or updating knowledge organization tools such as thesauri. Design/methodology/approach - The paper proposes a comprehensive methodology for thesaurus construction and maintenance combining shallow NLP with a clustering algorithm and an information visualization interface. The resulting system TermWatch, extracts terms from a text collection, mines semantic relations between them using complementary linguistic approaches and clusters terms using these semantic relations. The clusters are mapped onto a 2D using an integrated visualization tool. Findings - The clusters formed exhibit the different relations necessary to populate a thesaurus or ontology: synonymy, generic/specific and relatedness. The clusters represent, for a given term, its closest neighbours in terms of semantic relations. Practical implications - This could change the way in which information professionals (librarians and documentalists) undertake knowledge organization tasks. TermWatch can be useful either as a starting point for grasping the conceptual organization of knowledge in a huge text collection without having to read the texts, then actually serving as a suggestive tool for populating different hierarchies of a thesaurus or an ontology because its clusters are based on semantic relations. Originality/value - This lies in several points: combined use of linguistic relations with an adapted clustering algorithm, which is scalable and can handle sparse data. The paper proposes a comprehensive approach to semantic relations acquisition whereas existing studies often use one or two approaches. The domain knowledge maps produced by the system represents an added advantage over existing approaches to automatic thesaurus construction in that clusters are formed using semantic relations between domain terms. Thus while offering a meaningful synthesis of the information contained in the original corpus through clustering, the results can be used for knowledge organization tasks (thesaurus building and ontology population) The system also constitutes a platform for performing several knowledge-oriented tasks like science and technology watch, textmining, query refinement.

From tables to frames

Turning the current Web into a Semantic Web requires automatic approaches for annotation of existing data since manual approaches will not scale in general. We here present an approach for automatic generation of F-Logic frames out of tables which subsequently supports the automatic population of ontologies from table-like structures. The approach consists of a methodology, an accompanying implementation and a thorough evaluation. It is based on a grounded cognitive table model which is stepwise instantiated by our methodology.

Structural semantic interconnections: a knowledge-based approach to word sense disambiguation

Word Sense Disambiguation (WSD) is traditionally considered an Al-hard problem. A break-through in this field would have a significant impact on many relevant Web-based applications, such as Web information retrieval, improved access to Web services, information extraction, etc. Early approaches to WSD, based on knowledge representation techniques, have been replaced in the past few years by more robust machine learning and statistical techniques. The results of recent comparative evaluations of WSD systems, however, show that these methods have inherent limitations. On the other hand, the increasing availability of large-scale, rich lexical knowledge resources seems to provide new challenges to knowledge-based approaches. In this paper, we present a method, called structural semantic interconnections (SSI), which creates structural specifications of the possible senses for each word in a context and selects the best hypothesis according to a grammar G, describing relations between sense specifications. Sense specifications are created from several available lexical resources that we integrated in part manually, in part with the help of automatic procedures. The SSI algorithm has been applied to different semantic disambiguation problems, like automatic ontology population, disambiguation of sentences in generic texts, disambiguation of words in glossary definitions. Evaluation experiments have been performed on specific knowledge domains (e.g., tourism, computer networks, enterprise interoperability), as well as on standard disambiguation test sets.

A symbolic approach to automatic multiword term structuring

This paper presents a three-level structuring of multiword terms basing on lexical inclusion, WordNet similarity and a clustering approach. Term clustering by automatic data analysis methods offers an interesting way of organizing a domain’s knowledge structure, useful for several information-oriented tasks like science and technology watch, textmining, computer-assisted ontology population, Question Answering (Q–A). This paper explores how this three-level term structuring brings to light the knowledge structures from a corpus of genomics and compares the mapping of the domain topics against a hand-built ontology (the GENIA ontology). Ways of integrating the results into a Q–A system are discussed.

From Tables to Frames

Turning the current Web into a Semantic Web requires automatic approaches for annotation of existing data since manual approaches will not scale in general. We here present an approach for automatic generation of F-Logic frames out of tables which subsequently supports the automatic population of ontologies from table-like structures. The approach consists of a methodology, an accompanying implementation and a thorough evaluation. It is based on a grounded cognitive table model which is stepwise instantiated by our methodology.