Extracting Temporal Expressions from Unstructured Open Resources
Zagros Valizadeh Ardalan · 2015
Temporal information processing has received substantial attention in the last few years, due to the appearance of temporal expressions in search keywords and importance of them in the internet content. AETAS is an online tool for converting text into internally well-connected RDF linked data with resolution of temporal expressions. AETAS follows fully SOA architecture and accessible from web-service. It implements a novel approach for semantic representation and linked temporal graphs from natural language sentences. In this research, we present a demonstration of such a tool combining the normalized temporal expression from context with linguistic frame semantic and create linked RDF graph which time defined as an individual dimension. The tool is based on SUTIME which identify the temporal expressions and normalized them by TIMEX3 standard and WP2, linguistic processor which tokenize, lemmatize and represent the semantic of sentences. The output of AETAS is enriched stored RDF triples that have ability to visualize the events extracted from the web on timeline. A SPARQL layer has been provided in order to get the results of stored data and visualize them by TIMELINE JavaScript library. The output of the system can be used in different manners; Make a self-recursive system to increase the efficiency of temporal expression tagger and add temporal aspect and dimension into linked data world.