This is a demonstration of our newly released Python package NL2LTL which leverages the latest in natural language understanding (NLU) and large language models (LLMs) to translate natural language instructions to linear temporal logic (LTL) formulas. This allows direct translation to formal languages that a reasoning system can use, while at the same time, allowing the end-user to provide inputs in natural language without having to understand any details of an underlying formal language. The package comes with support for a set of default LTL patterns, corresponding to popular DECLARE templates, but is also fully extensible to new formulas and user inputs. The package is open-source and is free to use for the AI community under the MIT license.
NL2LTL – a Python Package for Converting Natural Language (NL) Instructions to Linear Temporal Logic (LTL) Formulas / Fuggitti, Francesco; Chakraborti, Tathagata. - 37:13(2023), pp. 16428-16430. (Intervento presentato al convegno Thirty-Seventh AAAI Conference on Artificial Intelligence tenutosi a Washington, DC, USA) [10.1609/aaai.v37i13.27068].
NL2LTL – a Python Package for Converting Natural Language (NL) Instructions to Linear Temporal Logic (LTL) Formulas
Fuggitti, Francesco
Primo
;
2023
Abstract
This is a demonstration of our newly released Python package NL2LTL which leverages the latest in natural language understanding (NLU) and large language models (LLMs) to translate natural language instructions to linear temporal logic (LTL) formulas. This allows direct translation to formal languages that a reasoning system can use, while at the same time, allowing the end-user to provide inputs in natural language without having to understand any details of an underlying formal language. The package comes with support for a set of default LTL patterns, corresponding to popular DECLARE templates, but is also fully extensible to new formulas and user inputs. The package is open-source and is free to use for the AI community under the MIT license.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
