Conceptual graph formalism for financial text representation

Abstract

We present an approach to automatically transform a financial text into conceptual graph formalism. The approach exploits the constituent structure of sentences and general English grammar rules to perform the transformation. We suggest face validation and traces as the evaluation method to be performed on the resulting formalism to validate its accuracy. We also discuss the potential manipulation and application of the constructed conceptual graph database.

Information Retrieval with a Simplified Conceptual Graph-Like Representation

“…For transforming the grammatical rules into CGs they use heuristics methods. Other researchers use link grammar [19,40] or dependency grammar [21]. In the latter work the authors use supervised learning to classify concepts, relations, and structures.…”

Aprendizaje de Reglas Encadenas para la Creación de Grafos Conceptuales

“…Las estructuras propias de esta categoría, a diferencia de las anteriores permiten incluir una mayor riqueza semántica. Dentro de estas estructuras se pueden catalogar, las redes semánticas [13], los lenguajes para descripción e intercambio de conocimiento como el Knowledge Interchange Format (KIF), el Resource Description Framework (RDF), el web ontology language (OWL) y los Grafos Conceptuales [12]. Estos últimos fueron diseñados para que su representación incluyera a demás detalles propios de la semántica, algunas de las bondades propias de las matemáticas.…”

Outlier detection in financial statements: a text mining method

“…Using this method the generator successfully identified nouns, verbs and adjectives, which were later built into concepts, whereas the prepositions were transformed into relations. The process is explained in detail in our previous paper [28]. The results of the generator were reformatted into a list of concepts and relation predicates following the formalism implemented in Conceptual Graph Interchange Format (CGIF) as shown in fig.…”