Results


Some new directions in robot problem solving

Classics

For the past several years research on robot problem-solving methods has centered on what may one day be called'simple' plans: linear sequences of actions to be performed by single robots to achieve single goals in static environments. This process of forming new subgoals and new states continues until a state is produced in which the original goal is provable; the sequence of operators producing that state is the desired solution. In the case of a single goal wff, the objective is quite simple: achieve the goal (possibly while minimizing some combination of planning and execution cost). The objective of the system is to achieve the single positive goal (perhaps while minimizing search and execution costs) while avoiding absolutely any state satisfying the negative goal.


Question-answering in English

Classics

To illustrate how this may be done in very simple cases we give rules which translate certain declarative sentences and questions involving the quantifiers'some', 'every', 'any', and'no' into a modified first-order predicate calculus, and answer the questions by comparing their translated forms with those of the declaratives. John kissed Mary (1) Did John kiss Mary? (5) We begin by describing a method for translating a modest subset of English into a slightly modified first-order predicate calculus -- modified just enough to provide a representation for questions. We would like to have rules which transcribe such declarative sentences into predicate calculus formulae, such as VxMxj (7') 3x-- The matrix will be preceded by a string of quantifiers and negations -- and possibly a question mark; we have found that the transcription rules which appear below produce unique and acceptable orderings of these symbols from unambiguous sentences of the specified type.


Automatic translation of languages since 1960: A linguist's view

Classics

Language was considered just a "bunch of words" and the primary task for early machine translation (MT) was to build machines large enough to hold all the words necessary in the translation process. These means included the printing out of the several possible solutions of ambiguous text segments to let the reader decide for himself the correct meaning, printing out the ambiguous source language text, and other temporary expedients. Particularly one must understand the rules under which such a complex system as human language operates and how the mechanism of this operation can be simulated by automatic means, i.e., without any human intervention at all. The second problem, the simulation of human language behavior by automatic means, is almost impossible to achieve, since language is an open and dynamic system in constant change and because the operation of the system is not yet completely understood.


The Syntactic Analysis of English by Machine

Classics

INTRODUCTION In this paper we describe a program which will assign deep and surface structure analyses to an infinite number of English sentences.1 The design of this program differs in several respects from that of other automatic parsers presently in existence. Among the most notable of these features is the program's ability to assign syntactic labels to an infinite number of words while operating with a finite dictionary. But undoubtedly the most important decision that resulted from our attempt to construct a model for the perception of syntactic structure was our decision that the program should assign both deep and surface structure analyses to sentences. There is a good deal of evidence to suggest that the efficiency with which human beings recognize the syntactic structure of sentences is to some extent the result of their ability, having heard part of a sentence, to predict the structure of the remainder.


BOXES: An experiment in adaptive control

Classics

In brief, we believe that programs for learning large games will need to have at their disposal good rules for learning small games. Each separate box functions as a separate learning machine: it is only brought into play when the corresponding board position arises, and its sole task is to arrive at a good choice of move for that specific position. The demon's task is to make his choices in successive plays in such a way as to maximise his expected number of wins over some specified period. By a development of Laplace's Law of Succession we can determine the probability, This defines the score associated with the node N. To make a move the automaton examines all the legal alternatives and chooses the move leading to the position having the highest associated score, ties being decided by a random choice.


Automatic speech recognition: a problem for machine intelligence

Classics

The outline is drawn of a hypothetical machine to recognise speech, comprising a basic recogniser working on short segments of acoustic waveform only, on to which may be added further structures to use knowledge of speaker characteristics, speech statistics, syntax rules, and semantics, in order to improve the recognition performance. Suppose one tried to implement a recogniser by telling the machine to store every new pattern it encountered together with a label telling it what word or words the pattern represented, with the intention of recognising an arbitrarily large vocabulary for an arbitrarily large proportion of the total population of speakers. The fifth section will describe briefly some work which is being carried out at Standard Telecommunication Laboratories towards implementing a real machine, and the final section will contain conclusions. If, as is highly probable for ASR, the speech is transmitted through a telephone link the problems of noise and distortion can be quite severe and include noises due to handling the handset, clicks and hisses in the speech band, limitation of the bandwidth to the range between 300 and 3400 cps, and pre-emphasis of the signal.


Semantic Message Detection for Machine Translation, Using an Interlingua

Classics

What is needed is a discipline which will study semantic message-connection in a way analogous to that in which metamathematics studies mathematical connection, and to that in which mathematical linguistics now studies syntactic connection. Research Used as Data for the Construction of T (a) Conceptual Dictionary for English The uses of the main words and phrases of English are mapped on to a classificatory system of about 750 descriptors, or heads, these heads being streamlined from Roget's Thesaurus. For Instance, a single card covers Disappoint, Disappointed, Disappointing, Disappointment. The two connectives, / ("slash") and: ("colon") and a word-order rule are used as in T to replace R.H. Richens' three subscripts, and every two pairs of elements are bracketted together, two bracketted pairs of elements counting as a single pair for the purpose of forming 2nd order brackets.


A model of the trust investment process

Classics

The investment process is a problem in decision-making under uncertainty. Our model, written as a computer program, simulates the proce- dures used in choosing investment policies for particular accounts, in evaluating the alternatives presented by the market, and in selecting the required portfolios. The analysis is based on the operations at a medium-sized national bank 1 and the decision-maker of our model is the trust imvestment officer.2 From A Simulation of Trust Investment, Englewood Cliffs, N.J.: Prentice-Hall, 1961.


Automatic indexing: An experimental inquiry

Classics

The fundamental thesis says, in effect, that statistics on kind, frequency, location, order, etc., of selected words are adequate to make reasonably good predictions about the subject matter of documents containing those words. Given this approach to automatic indexing, two problems present themselves, viz., the selection of clue words and the prediction techniques relating clue words and subject categories. Statistical data relating clue words and subject categories constitute hypotheses. Another and different class of documents was obtained and using the statistical data gathered initially, a machine was programmed to index automatically the documents in question.


A selected descriptor indexed bibliography to the literature on artificial intelligence

Classics

This listing is intended as an introduction to the literature on Artificial Intelligence, €”i.e., to the literature dealing with the problem of making machines behave intelligently. We have divided this area into categories and cross-indexed the references accordingly. Large bibliographies without some classification facility are next to useless. This particular field is still young, but there are already many instances in which workers have wasted much time in rediscovering (for better or for worse) schemes already reported. In the last year or two this problem has become worse, and in such a situation just about any information is better than none. This bibliography is intended to serve just that purpose-to present some information about this literature. The selection was confined mainly to publications directly concerned with construction of artificial problem-solving systems. Many peripheral areas are omitted completely or represented only by a few citations.IRE Trans. on Human Factors in Electronics, HFE-2, pages 39-55