A language for specifying program transformations

A language is described for specifying program transformations, from which programs can be generated to perform the transformations on sequences of code. The main objective of this work has been to develop a language that would allow the user to quickly and easily specify a wide range of transformations for a variety of programming languages. The rationale for the language constructs is given, as well as the details of an implementation which was prototyped using Prolog. Numerous examples of the language usage are provided     

A transportable authoring system

The technical transfer or CALCHEM material, a blend of laboratory and tutorial CAL in Chemistry, is commonly accomplished by movement from one computer system to another with little or no change (i.e. by transport) even though most of the programs are written in a “non-standard” language. A significant proportion of CAL activity genuinely needs special purpose CAL systems oriented towards the use of computers as an educational aid. Such systems provide facilities not immediately available in standard languages such as FORTRAN and BASIC. They can also aid the transfer of educational material.     

Episodic Logic: A comprehensive,natural representation for language understanding

A new comprehensive framework for narrative understanding has been developed. Its centerpiece is a new situational logic calledEpisodic Logic (EL), a knowledge and semantic representation well-adapted to the interpretive and inferential needs of general NLU. The most distinctive features of EL is its natural language-like expressiveness. It allows for generalized quantifiers, lambda abstraction, sentence and predicate modifiers, sentence and predicate reification, intensional predicates (corresponding to wanting, believing, making, etc.), unreliable generalizations, and perhaps most importantly, explicit situational variables (denoting episodes, events, states of affairs, etc.) linked to arbitrary formulas that describe them. These allow episodes to be explicitly related in terms of part-whole, temporal and causal relations. Episodic logical form is easily computed from surface syntax and lends itself to effective inference.     

A standard language for service delivery: Enabling understanding among stakeholders

In Integrated Service Delivery (ISD), multiple service providers have to collaborate in order to serve as a one-stop shop for their clients. Although technical standards have been met, collaboration is difficult. Service providers do not know what kind of information other providers need, are not aware of each other's processes or simply do not understand each other due to the use of ambiguous terms. In this paper, foundations for a language are developed to specify the requirements for ISD and enable the unambiguous understanding of these requirements. A combination of the standards Object-Role Modeling (ORM) and Semantics of Business Vocabulary and Business Rules (SBVR) is used to ensure human readability and to have the full expressive power of formal languages. Composed expressions are developed to express logical, temporal, and geographical requirements. This enables service providers to understand how, when, and where services need to be integrated. By utilizing these foundations to generate a standard language for ISD, service providers can collaborate and they can understand complex client requirements which lead to improved ISD.     

Natural language understanding by a robot: A pattern recognition problem

We present a program that understands Natural Language Commands, i.e. which have a free form but a well-defined semantic content. We show that by Structural Pattern Recognition techniques, the program “learns” the vocabulary and the structure of the sentences. An example is given, “the taxi driver robot”, which is directed by Natural Language Commands.     

A transportable extendable compiler

This report describes the development of a transportable extendable self-compiler for the language SIMPL-T. SIMPL-T is designed as the base language for a family of languages. The structure of the SIMPL-T compiler and its transportable bootstrap are described. In addition, the procedures for generating a compiler for a new machine and for boot-strapping the new compiler on to the new machine are demonstrated.     

A computer system capable of understanding a natural language

Cybernetics and Systems Analysis -     

A program design language based software maintenance tool

Program design languages are an increasingly important method of expressing the detailed design of a software system. Such languages can be modelled using a data structure known as a semantic net. This paper describes a maintenance tool for program design languages based on such a data structure. The tool allows the user to interrogate a semantic net using an interactive procedural language in order to derive information necessary for software maintenance. The technique upon which this tool is based is applicable to the maintenance of activities throughout the software lifecycle.     

Interpretable program specification language

In the paper, a domain-specific language of executable specifications is proposed. This language makes it possible to describe models of formalized subject domains in a graphical form, formulate computational problems on these models, and synthesize programs for solving these problems (including parallel ones) based on deductive inference in a special class of proposition calculus.     

A relational tsetlin machine with applications to natural language understanding

Journal of Intelligent Information Systems - Tsetlin machines (TMs) are a pattern recognition approach that uses finite state machines for learning and propositional logic to represent patterns. In...     

A medical Chatbot using machine learning and natural language understanding

Multimedia Tools and Applications - For people with busy schedules, travelling to and from a hospital for treatment is considerably time consuming, which leads them to ignore their health problems....     

Connectionist systems for natural language understanding

We will discuss various connectionist schemes for natural language understanding (NLU). In principle, massively parallel processing schemes, such as connectionist networks, are well-suited for modelling highly integrated forms of processing. The connectionist approach towards natural language processing is motivated by the belief that a NLU system should process knowledge from many different sources, e.g. semantic, syntactic, and pragmatic, in just this sort of integrated manner. The successful use of spreading activation for various disambiguation tasks in natural language processing models lead to the first connectionist NLU systems. In addition to describing in detail a connectionist disambiguation system, we will also discuss proposed connectionist approaches towards parsing and case role assignment. This paper is intended to introduce the reader to some of the basic ideas behind the connectionist approach to NLU. We will also suggest some directions for future research.     

The AT&T spoken language understanding system

Spoken language understanding (SLU) aims at extracting meaning from natural language speech. Over the past decade, a variety of practical goal-oriented spoken dialog systems have been built for limited domains. SLU in these systems ranges from understanding predetermined phrases through fixed grammars, extracting some predefined named entities, extracting users' intents for call classification, to combinations of users' intents and named entities. In this paper, we present the SLU system of VoiceTone/spl reg/ (a service provided by AT&T where AT&T develops, deploys and hosts spoken dialog applications for enterprise customers). The SLU system includes extracting both intents and the named entities from the users' utterances. For intent determination, we use statistical classifiers trained from labeled data, and for named entity extraction we use rule-based fixed grammars. The focus of our work is to exploit data and to use machine learning techniques to create scalable SLU systems which can be quickly deployed for new domains with minimal human intervention. These objectives are achieved by 1) using the predicate-argument representation of semantic content of an utterance; 2) extending statistical classifiers to seamlessly integrate hand crafted classification rules with the rules learned from data; and 3) developing an active learning framework to minimize the human labeling effort for quickly building the classifier models and adapting them to changes. We present an evaluation of this system using two deployed applications of VoiceTone/spl reg/.     

Module-level testing for natural language understanding

Conclusion We have examined a module-level evaluation methodology for natural language understanding, illustrating insights gained during implementation. It is possible to produce useful quantitative and qualitative results using such a methodology, provided certain pitfalls are avoided.     

A program structuring preprocessor for a macro assembly language

This paper deals with design considerations and implementation of a program structuring preprocessor for a macro assembly language. The macro assembly language is used for writing the code generation pass of a compiler. Macro instructions become lengthy, tedious and cumbersome when they incorporate some mild code improvement. This is chiefly because the macro assembly language lacks an adequate program structuring facility. Program structuring is a great help in improving ease of programming and the under-standability of the expansion control statements of a macro instruction in such a kind of programming. Considerations on the design of the source language and the outline of implementation are described. The design objective is ease of implementation and ease of use, and is fairly well satisfied by the language.