Initial implementation of natural language turn-based dialog system

  • Tagung:

    Konferenzartikel 

  • Autoren:

    Alexander Wachtel
    Sebastian Weigelt
    Walter F. Tichy

  • Summary

    Our prototype implements a natural language dialog system for Excel spreadsheets. The work is motivated by a pilot study which shows that novice users have difficulties with the formula language of Excel and need interactive assistance. JustLingo allows spreadsheet calculations in ordinary, written English. Furthermore, users can extend the system functionality by explaining of the calculations to the prototype. The keyword-based system analyzes the input using natural language processing techniques and translates it into Excel formulas. It asks for missing information such as operands and target cells and provides alternatives if there are ambiguities. It also handles references to previous inputs, allowing step-by-step construction of calculations. An evaluation shows that it properly resolves 82 % of references and correctly interprets 79,5 % of overall user input. Although far from perfect, the prototype demonstrates that computers may soon begin to take on simple, limited-domain programming tasks based on natural language input.

  • Jahr:

    2015 

Projekte
Titel

Bibtex

@inproceedings{WWT2015,
author={Alexander Wachtel, Sebastian Weigelt, Walter F. Tichy},
title={Initial implementation of natural language turn-based dialog system},
year=2015,
month=12,
booktitle={7th International conference on Intelligent Human Computer Interaction, IHCI 2015},
publisher={Elsevier B.V.},
abstract={Our prototype implements a natural language dialog system for Excel spreadsheets. The work is motivated by a pilot study which shows that novice users have difficulties with the formula language of Excel and need interactive assistance. JustLingo allows spreadsheet calculations in ordinary, written English. Furthermore, users can extend the system functionality by explaining of the calculations to the prototype. The keyword-based system analyzes the input using natural language processing techniques and translates it into Excel formulas. It asks for missing information such as operands and target cells and provides alternatives if there are ambiguities. It also handles references to previous inputs, allowing step-by-step construction of calculations. An evaluation shows that it properly resolves 82 % of references and correctly interprets 79,5 % of overall user input. Although far from perfect, the prototype demonstrates that computers may soon begin to take on simple, limited-domain programming tasks based on natural language input.},