Paper: Menu-Based Natural Language Understanding

ACL ID P83-1023
Title Menu-Based Natural Language Understanding
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 1983

This paper describes the NLMenu System, a menu-based natural language understanding system. Rather than requiring the user to type his input to the system, input to NLMenu is made by selec- ting items from a set of dynamically changing menus. Active menus and items are determined by a predictive left-corner parser that accesses a semantic grammar and lexicon. The advantage of this approach is that all inputs to the NLMenu System can be understood thus giving a 0% failure rate. A companion system that can automatically generate interfaces to relational databases is also discussed. relatively straightforward queries that PLANES could understand. Additionally, users did not successfully adapt to the system's limitations after some amount of use. One class of problem that caused negative and f...