Text Understanding Agents and the Semantic Web

Abstract

Abstract-We discuss the challenges involved in adapting the OntoSem natural language processing system to the Web. One set of tasks involves processing Web documents, translating their computed meaning representations from the OntoSem's native KR language into the Semantic Web language OWL, and publishing the results as Web pages and RSS feeds. Another set of tasks works in reverse -querying the Web for facts needed by OntoSem, translating them from OWL into OntoSem's native KR language and importing the results. A central problem underlying both sets of tasks is that of translating knowledge between OntoSem's KR language and ontologies and those of the Semantic Web. OntoSem2OWL has been developed as a translation system to support these translations. We describe SemNews, an implemented prototype application that demonstrates the process. It monitors RSS feeds of news stories, applies OntoSem to understand the text, and exports the computed facts back to the Web in OWL.

Ontology Importance towards Enhancing Suggestions in a News Recommender System for a Financial Investor

“…A solution would be by using Natural Language Processing (NLP) tools to convert natural language text into a structured representation thereby adding additional metadata in the RSS fields [7].…”

“…Other researchers [7] had implemented a prototype application to monitor RSS feeds of news stories, querying the Web for facts needed by OntoSem, translate them from OWL into OntoSems native KR language to understand the text, and exports the computed facts back to the Web in OWL. Yu et al [8] proposed a Web portal which was owned and managed by the specific user, located on the users local desktop or local network, and constructed based on semantic Web technology for satisfying the requirements of a user to all his relevant information.…”

A lexico-semantic pattern language for learning ontology instances from text

“…In the current body of literature, various pattern grammars are described that could be of use in for instance news processing frameworks [30,31] or general purpose information extraction tools [32,33,34,35,36]. These patterns are based on linguistic or lexical knowledge, as well as a priori human knowledge regarding the contents or topic of the text that is to be processed.…”

Financial News Analysis Using a Semantic Web Approach

“…SemNews (Java, Finin, & Nirenburg, 2006a) is a project focused on applying a complex text understanding process on the news items found on different RSS feeds. It extracts significant information and stores it in a Semantic Web environment, available for browsing and querying.…”

“…The NLP system used by SemNews is called OntoSem (Java, Finin, & Nirenburg, 2006b). With this system, the text gets processed through three stages: a syntactic, semantics and finally a pragmatic analysis.…”