Expanding the Horizons of Natural Language Interfaces

Current natural language interfaces have concentrated largely on determining the literal "meaning" of input from their users. While such decoding is an essential underpinning, much recent work suggests that natural language interlaces will never appear cooperative or graceful unless they also incorporate numerous non-literal aspects of communication, such as robust communication procedures. This toaper defends that view. but claims that direct imitation of human performance =s not the best way to =mplement many of these non-literal aspects of communication; that the new technology of powerful personal computers with integral graphics displays offers techniques superior to those of humans for these aspects, while still satistying human communication needs. The paper proposes interfaces based on a judicious mixture of these techniques and the still valuable methods of more traditional natural language interfaces. 1. I n t roduc t ion Most work so far on natural language communication between man and machine has dealt with its literal aspects. That is. natural language interlaces have implicitly adopted the position that their user's input encodes a request for intormation of; action, and that their job is tO decode the request, retrieve the information, or perform the action, and provide appropriate output back to the user. This is essentially what Thomas [24J cnlls the Encoding-Decoding model of conversation. While literal interpretation is a basic underpinning of communication, much recent work in artificial intelligence, linguistics, and related fields has shown that it is tar from the whole story in human communication. For example, appropriate interpretation of an utterance depends on assumptions about the speaker's intentions, and conversely, the sl.)eaker's goals influence what is said (Hobbs [13J, Thomas [24]). People often make mistakes in speaking and listening, and so have evolvod conventions for affecting regalrs-(Schegloll et el. [20J). There must also be a way of regulating the turns of participants in a conversation (Sacks et el. [10t). This is just a sampling of what we will collectively call non literal ~lspects ol communicat ion. The primary reason for using natural language in man-machine communication is to allow the user to express himsell mtturallyo and without hawng to learn a special language. However, it is becoming clear that providing for n,'ttural expression means dealing will1 tile non-literal well as the literal aspects ol communication; float the ability to interpret natural language literaUy does not in itself give a man-machine interlace the ability to communicate naturally. Some work on incorporating these non-literal aspects of communication into man-machine interfaces has already begun([6, 8, 9, 15, 21, 25]). The position I wish to stress in this paper is that natural language interfaces will never perform acceptably unless they deal with the non-literal as well as the literal aspects of communication: that without the non-literal aspects, they will always appear uncooperative, inflexible, unfriendly, and generally stupid to their users, leading to irritation, frustration, and an unwillingness to continue to be a user. This pos=tion is coming to be held fairly widely. However, I wish to go further and suggest that, in building non-literal aspects of communication into natural-language interfaces, we should aim for the most effective type of communication rather than insisting that the interface model human performance as exactly as possible. I believe that these two aims are not necessarily the same. especially given certain new technological trends (.lis(J ti ,'~s£~l below. Most attempts to incorporate non-literal aspects of communication into natural language interlaces have attempted to model human performance as closely as possible. The typical mode of communication in such an interface, in which system and user type alternately on a single scroll of pager (or scrolled display screen), has been used as an analogy to normal spoken human conversation in Wlllcll contmunicallon takes place over a similar half-duplex channel, i.e. a channel that only one party at a time can use witllout danger of confusion. Technology is outdating this model. Tl~e nascent generation of powerful personal computers (e.g. the ALTO ~23} or PERQ [18J) equipped with high-resolution bit-map graphics display screens and pointing devices allow the rapid display of large quantities of information and the maintenance of several independent communication channels for both output (division ol the screen into independent windows, highlighting, and other graphics techniques), and input (direction of keyboard input to different windows, poinling ,~put). I believe that this new technology can provide highly effective, natural language-based, communication between man and machine, but only il the half-duplex style of interaction described above is dropped. Rall~er than trying to imitate human convets~mon d=rectty, it will be more fruitful to use the capabilities of this new technology, whicl~ in some respects exceed those possessed by humans, to achieve the snme ends as the non-literal aspects of normal human conversation. Work by. for instance, Carey [31 and Hiltz 1121 shows how adaptable people aro to new communication situ~.~tlons, and there is every reason Io believe that people will adapt well to an interaction in which their communication ne~,ds are satisfied, even if they are satislied in a dilterent way than in ordinary human conversation. In the remainder of the paper I will sketch some human communication needs, and go on to suggest how they can be satisfied using the technology outlined above. 2. Non-Li tera l Aspects of Commun ica t ion In this section we will discuss four human communication needs and tile non-literal aspects of communication they have given rise to: • non-grammatical utterance recognition • contextually determined interpretation • robust communication procedures