Formal Validation for Natural Language Programming using Hierarchical Finite State Automata

Yue Zhan, Michael Hsiao

Abstract

Natural language programming (NLPr) is a sub-field of natural language processing (NLP) that provides a bridge between natural languages (NL) and programming languages (PL), allowing users to design programs in the form of structured NL documents. Due to the imprecise and ambiguous nature of NL, it is essential to ensure the correctness of translation for critical applications where errors are unacceptable. Machine learning-based approaches for error checking are insufficient as it can be difficult for even the most sophisticated models to capture all the relevant intricacies of a natural language. Automata offer a formalism that has been used in compiling programming languages, and this paper extends automata-based methods to validating programs written in natural languages. In particular, we propose a hierarchically structured finite-state automaton, modeled based on domain-specific knowledge, for NLPr input validation and semantic error reporting. Experimental results from validating a set of collected NL sentences show that the proposed validation and error reporting can catch the unexpected input components while validating the semantics.

Download


Paper Citation


in Harvard Style

Zhan Y. and Hsiao M. (2021). Formal Validation for Natural Language Programming using Hierarchical Finite State Automata.In Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI, ISBN 978-989-758-484-8, pages 506-515. DOI: 10.5220/0010388905060515


in Bibtex Style

@conference{nlpinai21,
author={Yue Zhan and Michael Hsiao},
title={Formal Validation for Natural Language Programming using Hierarchical Finite State Automata},
booktitle={Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI,},
year={2021},
pages={506-515},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010388905060515},
isbn={978-989-758-484-8},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI,
TI - Formal Validation for Natural Language Programming using Hierarchical Finite State Automata
SN - 978-989-758-484-8
AU - Zhan Y.
AU - Hsiao M.
PY - 2021
SP - 506
EP - 515
DO - 10.5220/0010388905060515