Menu-Based Natural Language Understanding

MENU-BASED NATURAL LANGUAGE UNDERSTANDING Harry R. Tennant, Kenneth M. Ross, Richard M. Saenz, Craig W. Thompson, and James R. Miller Computer Science Laboratory Central Research Laboratories Texas Instruments Incorporated Dallas, Texas ABSTRACT 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 false user expectations was the user's ability to distinguish between the limitations in the system's conceptual coverage and the system's linguistic coverage. Often, users would attempt to para- phrase a sentence many times when the reason for the system's lack of understanding was due to th~ fact that the system did not have data about the query being asked (i.e. the question exceeded the conceptual coverage of the system). Conversely, users' queries would often fail because they were phrased in a way that the system could not handle (i.e. the question exceeded the linguistic coverage of the system). I INTRODUCTION Much research into the building of natural language interfaces has been going on for the past 15 years. The primary direction that this re- search has taken is to improve and extend the capabilities and coverage of natural language interfaces. Thus, work has focused on constructing and using new formalisms (both syntactically and semantically based) and on improving the grammars and/or semantics necessary for characterizing the range of sentences to be handled by the system. The ultimate goal of this work is to give natural language interfaces the ability to understand larger and larger classes of input sentences. Tennant (1980) is one of the few attempts to consider the problem of evaluating natural language interfaces. The results reported by Tennant concerning his evaluation of the PLANES System are discouraging. These results show that a major problem with PLANES was the negative expectations created by the system's inability to understand input sentences. The inability of PLANES to handle sentences that were input caused the users to infer that many other sentences wou|d not be correctly handled. These inferences about PLANES' capabilities resulted in much user frus- tration because of their very limited assumptions about what PLANES could understand. It rendered them unable to successfully solve many of the problems they were assigned as part of the evalu- ation of PLANES, even though these problems had been specifically designed to correspond to some The problem pointed out by Tennant seems to be a general problem that …

Content truncated to 500 words