Difficulty Estimator for Converting Natural Language into First Order Logic

Abstract

The NLtoFOL system is an interactive web-based system for learning to convert natural language (NL) sentences into first order logic (FOL). In this paper, we present a difficulty estimating expert system that determines the difficulty level of a sentence’s conversion process. Our approach is based on the complexity of the corresponding FOL formula instead of the NL sentence itself. Parameters like the number, the type and the order of quantifiers, the number of implications and the number of different connectives are taken into account. Experimental results show that for a significant part of sentences the difficulty estimating system produces the correct outputs.