Abstract
Information Extraction (IE) is the task of automatically organizing in a structured form data extracted from free text documents. In several contexts, it is often desirable that the extracted data are then organized according to an ontology, which provides a formal and conceptual representation of the domain of interest. Ontologies allow for a better data interpretation, as well as for their semantic integration with other information, as in Ontology-based Data Access (OBDA), a popular declarative framework for data management where an ontology is connected to a data layer through mappings. However, the data layer considered so far in OBDA has consisted essentially of relational databases, and how to declaratively couple an ontology with unstructured data sources is still unexplored. By leveraging the recent study on document spanners for rule-based IE by Fagin et al., in this paper, we propose a new framework that allows to map text documents to ontologies, in the spirit of OBDA. We investigate the problem of answering conjunctive queries in this framework. For ontologies specified in the Description Logics [Formula: see text] and [Formula: see text], we show that the problem is polynomial in the size of the underlying documents. We also provide algorithms to solve query answering by rewriting the input query on the basis of the ontology and its mapping toward the source documents. Through these techniques, we pursue a virtual approach, similar to that typically adopted in OBDA, which allows us to answer a query without having to first populate the entire ontology. Interestingly, for [Formula: see text], both the spanners used in the mapping and the one computed by the rewriting algorithm belong to the same class of expressiveness. This holds also for [Formula: see text], modulo some limitations on the form of the mapping. These results say that in these cases our framework can be easily implemented by decoupling ontology management and document access, which can be delegated to an external IE system able to process the extraction rules we use in the mapping.
Highlights
One of the basic problems of the data-centric information era is the processing of huge amount of unstructured data
We demonstrate MASTRO SYSTEM-T, a new Ontology Mediated Information Extraction (OMIE) system born from a collaboration between the University of Rome “La Sapienza” and IBM Research Almaden
After a brief presentation of the system architecture and its main functionalities, we show an OMIE application involving a set of real-world financial text documents coming from the U.S repository of Electronic Data Gathering, Analysis and Retrieval system (EDGAR)
Summary
One of the basic problems of the data-centric information era is the processing of huge amount of unstructured data. Information Extraction (IE) provides support to this problem It refers to the task of automatically organizing gathered data into a structured representation, typically a spread-sheet or a database [11, 6, 4]. Rule-based, and learning based approaches for IE have been proposed along the years, leveraging techniques from NLP, machine learning, computational linguistics, databases and knowledge representation (see, e.g., [7, 2, 5, 1]) In this frame of reference, ontologies, which provide formal and explicit specifications of conceptualizations, have been recognized to play an important role in IE [12]. We discuss this feature together with some preliminary experiments that show how ontology reasoning allow us to increase the quality of the extracted data
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
