FrameNet CNL: a Knowledge Representation and Information Extraction Language

TL;DR

This paper introduces FrameNet-CNL, a framework that extracts knowledge from natural language documents into a Frame-ontology, enabling automatic generation of unambiguous, multilingual paraphrases and bridging information extraction with controlled natural language.

Contribution

It presents a novel FrameNet-based knowledge representation framework that integrates information extraction with controlled natural language generation for multilingual applications.

Findings

Implemented a state-of-the-art parser for news agency use

Demonstrated automatic generation of FrameNet-CNL paraphrases in multiple languages

Proposed that FrameNet-CNL could standardize language in news writing

Abstract

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.