SPARQL/T: A query language with SPARQL’s syntax for semantic mining of textual complaints

Extracting information from complaints, either scraped from the Web or received directly from the client, is a necessity of many companies nowadays. The aim is to find inside them some actionable knowledge. To this purpose, verbal phrases must be analyzed, as many complaints refer to actions improperly performed. The Semantic Roles of the actions (who did what to whom) and the Named Entities involved need to be extracted. Moreover, for the correct interpretation of the claims, the software should be able to deal with some background knowledge (for example, a product’s ontology). Although there are already many libraries and out of the shelf tools that allow tackling these problems singularly, it may be hard to find one that includes all the needed tasks. We propose here a query language that adopts the syntax of SPARQL to extracts information from natural language documents, pre-annotated with NLP information. The language provides the user with a simple and uniform interface to the most useful NLP tasks, isolating him or her from the details of the specific implementation. We argue that a query language is much easier and intuitive (from a laymen point of view) than an imperative one. Moreover, the adoption of the SPARQL syntax allows to seamlessly mix, inside the same query, NLP patterns with traditional RDF/OWL ones, simplifying the integration with Semantic Web technologies