ProNat: An Agent-Based System Design for Programming in Spoken Natural Language.
Authors: Weigelt, Sebastian, and Walter F. Tichy
Conference: IEEE/ACM 37th IEEE International Conference on Software Engineering (ICSE), 2015
Abstract: The emergence of natural language interfaces has led to first attempts of programming in natural language. We present ProNat, a tool for script-like programming in spoken natural language (SNL). Its agent-based architecture unifies deep natural language understanding (NLU) with modular software design. ProNat focuses on the extraction of processing flows and control structures from spoken utterances. For evaluation we have begun to build a speech corpus. First experiments are conducted in the domain of domestic robotics, but ProNat's architecture makes domain acquisition easy. Test results with spoken utterances in ProNat seem promising, but much work has to be done to achieve deep NLU.
@INPROCEEDINGS{7203085,
author={Weigelt, S. and Tichy, W.F.},
booktitle={Software Engineering (ICSE), 2015 IEEE/ACM 37th IEEE International Conference on},
title={Poster: ProNat: An Agent-Based System Design for Programming in Spoken Natural Language},
year={2015},
volume={2},
pages={819-820},
keywords={authoring languages;natural language interfaces;programming languages;software agents;software architecture;software tools;NLU;ProNat architecture;SNL;agent-based architecture;agent-based system design;control structures;deep natural language understanding;domestic robotics;modular software design;natural language interfaces;processing flow extraction;script-like programming;speech corpus;spoken natural language;spoken utterances;Natural languages;Ontologies;Programming;Robots;Speech;Speech recognition;Unified modeling language;agent-based software design;end user programming;natural language processing;natural lanuage understanding;ontology;programming in natural language;robotics},
doi={10.1109/ICSE.2015.264},
month={May},}