Implementing Controlled Languages in GF

Abstract. Addressing tax fraud has been taken increasingly seriously, but most attempts to uncover it involve the use of human fraud experts to identify and audit suspicious cases. To identify such cases, they come up with patterns which an IT team then implements to extract matching instances. The process, starting from the communication of the patterns to the developers, the debugging of the implemented code, and the refining of the rules, results in a lengthy and errorprone iterative methodology. In this paper, we present a framework where the fraud expert is empowered to independently design tax fraud patterns through a controlled natural language implemented in GF, enabling immediate feedback reported back to the fraud expert. This allows multiple refinements of the rules until optimised, all within a timely manner. The approach has been evaluated by a number of fraud experts working with the Maltese Inland Revenue Department.

Section: Fig 1 Fraud Detection Processmentioning

confidence: 99%

Section: A Fraud Monitoring Architecturementioning

confidence: 99%

A Controlled Natural Language for Tax Fraud Detection

Calafato

Colombo

Pace

2016

“…GF can cope with a variety of CNLs as well as boost the development of new ones. In [17], the authors reverse engineer ACE for GF in order to demonstrate how portable CNLs are to the GF framework as well as how CNLs can be targeted to other natural languages. ACE is ported from English to five other natural languages.…”

Section: Grammatical Framework Gfmentioning

confidence: 99%

“…This has boosted the uptake of GF and resulted in many comprehensive applications. GF applications range from mathematical proofing, dialog systems, patent translation [19], multilingual wikis and multilingual generation in the culture heritage domain [17] [20]. In addition, there have been recent efforts to cater for semantic web ontologies in GF.…”

Section: Grammatical Framework Gfmentioning

confidence: 99%

A Brief State of the Art of CNLs for Ontology Authoring

Safwat

Davis

2014

“…Attempto Controlled English [4]), another research direction has focused on enhancing the CNL parsing and generation techniques to/from some Abstract Knowledge Representation (AKR) format (e.g. abstract grammar in Grammatical Framework [8]) to the point where the borderline between the natural language and CNL becomes blurred. The blurring occurs, when the information extraction parsers become capable of extracting the correct AKR not only from CNL, but also (to substantial degree) from the natural language (NL) documents.…”

Section: Introductionmentioning

confidence: 99%

FrameNet CNL: A Knowledge Representation and Information Extraction Language

Bārzdiņš

2014

The paper presents a FrameNet-based information extraction and knowledge representation framework, called FrameNet-CNL. The framework is used on natural language documents and represents the extracted knowledge in a tailor-made Frame-ontology from which unambiguous FrameNet-CNL paraphrase text can be generated automatically in multiple languages. This approach brings together the fields of information extraction and CNL, because a source text can be considered belonging to FrameNet-CNL, if information extraction parser produces the correct knowledge representation as a result. We describe a state-of-the-art information extraction parser used by a national news agency and speculate that FrameNet-CNL eventually could shape the natural language subset used for writing the newswire articles.