Danilo S. Carvalho

Financial credit analysis via a clustering weightless neural classifier

Credit analysis is a real-world classification problem where it is quite common to find datasets with a large amount of noisy data. State-of-the-art classifiers that employ error minimisation techniques, on the other hand, require a long time to converge, in order to achieve robustness. This paper explores ClusWiSARD, a clustering customisation of the WiSARD weightless neural network model, applied to two different credit analysis real-world problems. Experimental evidence shows that ClusWiSARD is very competitive with Support Vector Machine (SVM) w.r.t. accuracy, with the advantage of being capable of online learning. ClusWiSARD outperforms SVM in training time, by two orders of magnitude, and is slightly faster in test time.

Representing Texts as Contextualized Entity-Centric Linked Data Graphs

The integration of a small fraction of the information present in the Web of Documents to the Linked Data Web can provide a significant shift on the amount of information available to data consumers. However, information extracted from text does not easily fit into the usually highly normalized structure of ontology-based datasets. While the representation of structured data assumes a high level of regularity, relatively simple and consistent conceptual models, the representation of information extracted from texts need to take into account large terminological variation, complex contextual/dependency patterns, and fuzzy or conflicting semantics. This work focuses on bridging the gap between structured and unstructured data, proposing the representation of text as structured discourse graphs (SDGs), targeting an RDF representation of unstructured data. The representation focuses on a semantic best-effort information extraction scenario, where information from text is extracted under a pay-as-you-go data quality perspective, trading terminological normalization for domain-independency, context capture, wider representation scope and maximization of textual information capture.

On the Semantic Representation and Extraction of Complex Category Descriptors

Natural language descriptors used for categorizations are present from folksonomies to ontologies. While some descriptors are composed of simple expressions, other descriptors have complex compositional patterns (e.g. ‘French Senators Of The Second Empire’, ‘Churches Destroyed In The Great Fire Of London And Not Rebuilt’). As conceptual models get more complex and decentralized, more content is transferred to unstructured natural language descriptors, increasing the terminological variation, reducing the conceptual integration and the structure level of the model. This work describes a representation for complex natural language category descriptors (NLCDs). In the representation, complex categories are decomposed into a graph of primitive concepts, supporting their interlinking and semantic interpretation. A category extractor is built and the quality of its extraction under the proposed representation model is evaluated.

Graphia: Extracting Contextual Relation Graphs from Text

This demo presents Graphia, an information extraction pipe-line targeting an RDF representation of unstructured data in the form of structured discourse graphs (SDGs). It combines natural language processing and information extraction techniques with the use of linked open data resources and semantic web technologies to enable discourse representation as a set of contextualized relationships between entities.

Extracting Semantic Information from Patent Claims Using Phrasal Structure Annotations

The rapid change of trading values from tangible assets to Intelectual Property has put both businesses and academia in a race to acquire and protect the rights to exploit such property. This is mainly accomplished in the form of patent issuing by the governments, being time consuming and complicated due to the vast amount of documents that need to be analyzed in order to assert the novelty or validity of a patent application. Patent information retrieval research is thus growing quickly to support document analysis across multiple domains and information systems. One of the big challenges in patent analysis is the identification of the elements of innovation (concepts, processes, materials) and the relations between them, in the patent text. This paper presents a method for extracting semantic information from patent claims by using semantic annotations on phrasal structures, abstracting domain ontology information and outputting ontology-friendly structures to achieve generalization. An extraction system built upon the method is briefly evaluated on a document sample from INPI, the Brazilian patent office, a challenging information source.