---
title: "TULIPS - Teachable, Understanding Natural Language Input Problem-Solver"
authors:
  - "Michael G. Malkovsky"
doi: ""
url: "https://ijcai.org/proceedings/1975/63"
pdf: "https://ijcai.org/proceedings/1975/0063.pdf"
venue: "Proceedings of the Fourth International Joint Conference on Artificial Intelligence"
year: 1975
pages: "397-399"
track: "Natural Language Understanding"
keywords:
---

# TULIPS - Teachable, Understanding Natural Language Input Problem-Solver

Michael G. Malkovsky

*Proceedings of the Fourth International Joint Conference on Artificial Intelligence*, pages 397-399.

## Abstract

This paper describes the principal features of TULIPS program designed as a widely-oriented AI system that accepts natural language (NL) input. NL processor of TULIPS is guided by information represented in models of current "external world" domain and of current user and utilizes deductive and inductive mechanisms. These features allow the program: to discover the most relevant interpretation of an input, to extract the descriptions of user's goals from NL utterances, and to generate the so-called T-£roblems ( T for TULIPS). Having solved t em TULIPS not only answers user's request but also learns new knowledge on its environment and improves its own mechanisms.