Enhancing Textual Knowledge Discovery using a Context-Awareness Approach

Semantic relation extraction has been a known branch in Natural language processing allowing the identification of relations between words. Knowledge-based approaches including wordnet and pattern matching approaches such as Hearst for hypernyms are used among many others. The search for relations is limited to sentences which avert the rest of the text narrowing the semantic relation extraction. In this paper, we introduce the use of context for improving the extraction using global information from the text and domain ontology.