Conference Paper

A Framework for Integrating Deep and Shallow Semantic Structures in Text Mining.

DOI: 10.1007/978-3-540-45224-9_110 Conference: Knowledge-Based Intelligent Information and Engineering Systems, 7th International Conference, KES 2003, Oxford, UK, September 3-5, 2003, Proceedings, Part I
Source: DBLP


Recent work in knowledge representation undertaken as part of the Semantic Web initiative has enabled a common infrastructure (Resource De- scription Framework (RDF) and RDF Schema) for sharing knowledge of on- tologies and instances. In this paper we present a framework for combining the shallow levels of semantic description commonly used in MUC-style informa- tion extraction with the deeper semantic structures available in such ontologies. The framework is implemented within the PIA project software called Ontol- ogy Forge. Ontology Forge offers a server-based hosting environmentfor ontolo- gies, a server-side information extraction system for reducing the effort of writ- ing annotations and a many-featured ontology/annotation editor. We discuss the knowledge framework, some features of the system and summarize results from extended named entity experiments designed to capture instances in texts using support vector machine software.

5 Reads
  • Source
    • "Our overall goal in the Ontology Express project is to provide an enhancement to Open Ontology Forge (OOF) [5], an integrated ontology construction, content annotation and information extraction tool, to aid experts in synthesizing their intuitions about domain concepts, properties and relations. Ontology construction proceeds from a top-down specification of a core DSO by the domain expert supported by Ontology Express which discovers candidate concepts, relations and properties from a document collection. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Text mining has an important role to play in aiding ex-perts to construct domain specific ontologies by highlighting the im-portant classes, properties and relations that occur within large text collections. In this paper we propose a systematic framework for dis-covery of ontological types using typing information complemented with statistical filtering. Preliminary experiments are conducted on three corpora in the domain of molecular biology and results show that the top level types we obtain closely meet the intuitions and ex-pectations of domain experts.
  • Source
    • "Regarding the link of our tool to the ontology, the most relevant work seems to be the Ontology Forge System described in (Collier, 2003). However, that environment is more an ontology creation and population (ontology expansion) tool focused mainly on named entities, while our Annotation Editor targets the domain expert's real needs in marking up basic semantic elements and events, using the ontology as a resource rather than an end- product. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Text Mining is a relatively new area of research, very interesting for both computational linguists and data miners. It involves collecting and analyzing quantities of textual data by domain experts, whose main task is the manual revision of markup. We describe a suite of tools used to simplify the process: the Parmenides System that consists of data warehouse, ontology, semi-automatic information extraction and data mining tools. Here we focus on the Annotation Editor which incorporates linguistic tools that initialize the markup automatically.
  • Source
    • "The Ontology Forge allows human experts to create taxonomies and axioms, and by providing a small set of annotated examples, machine learning can take over the role of instance capturing though information extraction technology. [6] Of course knowledge does not only reside in experts who create taxonomies. Much can be extracted from the millions of online forums that have mushroomed in recent years. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper reviews the developments in the past three years in the topics of Knowledge Capture, Knowledge Representation, and Knowledge Visualization, from a semantic Web ontology perspective. The paper tries to show that these three topics blend or even overlap one another. Concept Mapping is one particular unifying theme. The paper will try to shed light on this by reviewing several prototypes, leading to a discussion of research directions that aims to conclude that graphical representations will play a key role in KC, KR, and KV and the semantic Web. Moreover, the future of these fields will make use of both semiotics as well as the design of collaborative spaces—in addition to the technology that underlies them.
Show more