Improving the Diproche CNL through autoformalization via GPT-3

03/12/2023
by   Merlin Carl, et al.
0

The Diproche system is an automated proof checker for texts written in a controlled fragment of German, designed for didactical applications in classes introducing students to proofs for the first time. The first version of the system used a controlled natural language for which a Prolog formalization routine was written. In this paper, we explore the possibility of prompting large language models for autoformalization in the context of Diproche, with encouraging first results.

READ FULL TEXT
research
05/09/2016

The Controlled Natural Language of Randall Munroe's Thing Explainer

It is rare that texts or entire books written in a Controlled Natural La...
research
11/14/2022

Towards a Mathematics Formalisation Assistant using Large Language Models

Mathematics formalisation is the task of writing mathematics (i.e., defi...
research
11/17/2022

Efficiency of Learning from Proof Blocks Versus Writing Proofs

Proof Blocks is a software tool that provides students with a scaffolded...
research
02/08/2022

Natural Language Proof Checking in Introduction to Proof Classes – First Experiences with Diproche

We present and analyze the employment of the Diproche system, a natural ...
research
06/05/2023

Easy-to-Read in Germany: A Survey on its Current State and Available Resources

Easy-to-Read Language (E2R) is a controlled language variant that makes ...
research
03/14/2019

Complexity-entropy analysis at different levels of organization in written language

Written language is complex. A written text can be considered an attempt...
research
08/22/2023

Using ChatGPT as a CAT tool in Easy Language translation

This study sets out to investigate the feasibility of using ChatGPT to t...

Please sign up or login with your details

Forgot password? Click here to reset