Unifying Speech and Computation

Abstract


A novel approach to programming computing machinery is demonstrated by the EnguageTM language engine: programming by utterance. The running of a command is modeled as a deductive process; the mechanism by which meaning is ascribed to utterance—induction—is described. A full example of the factorial function is given. The paper then develops utterance not only as a form of issuing commands to hardware, but also of storing, retrieving, and manipulating spoken information—a programmable UI. Because such utterances can be generated by speech-to-text software, such interactive computation does not require a program as a written artifact.

 

Unifying Speech and Computation | Request PDF. Available from: https://www.researchgate.net/publication/326140012_Unifying_Speech_and_Computation.

Programming Without Program or How to Program in Natural Language Utterances

Abstract


A new approach to programming computing machinery is presented, representing programming without a written software artifact—a program. The availability of numerous speech-to-text services, gives access to practical voice recognition. Enguage™is an open, programmable speech understanding engine, prototyped in Java, which is built into an app on Google Play, acting entirely as its user interface. Thus, devices can be instructed, and present results, in natural language utterances; engineers are afforded their own concepts and associated conversations. This paper shows how this can be turned in on itself, programming the interpretation of utterances, itself, purely through utterance.

Programming Without Program or How to Program in Natural Language Utterances | Request PDF. Available from: https://www.researchgate.net/publication/321172326_Programming_Without_Program_or_

How_to_Program_in_Natural_Language_Utterances.

What Google Doesn’t Know

Abstract


Martin Wheatman, winner of the 2016 BCS SGAI Machine Intelligence Competition, describes a replacement for the GUI metaphor through using natural language to make our smartphones chatty.
Wheatman, Martin. (2017). What Google Doesn’t Know. ITNOW. 59. 48-49. 10.1093/itnow/bwx022.

Context-Dependent Pattern Simplification by Extracting Context-Free Floating Qualifiers

Abstract


Qualification may occur anywhere within a temporal utterance. To reduce the ensuing pattern complexity for context-dependent systems such as Enguage \(^{\mathrm{TM}}\), it is necessary to remove the qualified value from the utterance; rendering the utterance atemporal and presenting the value as the contextual variable when. This is possible because a qualifier—at 7:30 or until today—is immediately recognisable as such if preceding a time value: when is context-free. This appropriation gives insight into the nature of the context-dependent processing of habitual natural language. While the difference between the resultant concepts—how many coffees do I have and how old am I—is perhaps not that great despite their differing origins, this work ensures the mediation system remains practical and effective. This research is informed by a prototype for the health-tech app Memrica Prompt in support of independent living for people with early stage dementia.

Context-Dependent Pattern Simplification by Extracting Context-Free Floating Qualifiers | Request PDF. Available from: https://www.researchgate.net/publication/309687810_Context-Dependent_Pattern_Simplification_by_Extracting_Context-Free_Floating_Qualifiers.

A Pragmatic Approach to Disambiguation in Text Understanding

Abstract


This paper describes a novel disambiguation mechanism for a text understanding system, which utilizes a general correction function, also described. This mechanism is comprised of: contextual ordering; transactional persistent memory; and, interactivity aligning machine action with user intent. The latter clearly demonstrates the use of language at a Pragmatic level – directedness toward user intent is afforded, purely through a speech interface. This work is supported by a Java implementation enguage and the iNeed app.

A Pragmatic Approach to Disambiguation in Text Understanding | Request PDF. Available from: https://www.researchgate.net/publication/305524776_A_Pragmatic_Approach_to_

Disambiguation_in_Text_Understanding.

If We Are Holding Hands, Whose Hand Am I Holding? An Autopoietic Conceptual Analysis System

Abstract


This paper presents the rationale for a prototype which performs concept-based linguistic analysis of utterances, inspired by Ronald Stamper’s approach to Informatics. Concepts, that about which we can speak, are defined by a linguistically-neutral repertoire of phrasal analysis patterns (representamen) and intentional utterances (interpretant). On a match, the associated intentions are internally uttered (semiosis); thus, specific concepts inform more general concepts. The concept of conceptualization grounds this linguistic analysis into a three-tiered space of entities and attributes (objects). Concepts are also self-described: the concept of autopoiesis uses a repertoire of 11 utterances to attribute intentions to phrasal analysis patterns. The concept of conceptualism allows hypothetical states of affairs (i.e. those which do not correspond to the state of affairs) to be asserted, such as the analytic question in the title.
Wheatman, Martin. (2015). If We Are Holding Hands, Whose Hand Am I Holding? An Autopoietic Conceptual Analysis System. 885-895. 10.1007/978-3-642-40660-7_132.

An Autopoietic Repertoire

Abstract


This paper presents a strategy for natural language processing in natural language. Using a concept as a unit of conversation, defined by a repertoire of phrases, it describes the concept of autopoiesis: a repertoire for the construction of repertoires. A minimal repertoire, representing a shopping list app, is described. This is followed by a specification of the autopoietic repertoire, followed by the full repertoire of the shopping list. The advantages of this approach is basically two-fold: a natural language specification is self-evident; moreover, it results in a rich, tiered interface of repertoires supporting repertoires. This paper is validated by an aural information system, publicly available on various mobile platforms.
Wheatman, Martin. (2014). An Autopoietic Repertoire. 165-170. 10.1007/978-3-319-12069-0_11.

A Semiotic Analysis of If we are holding hands, whose hand am I holding?

Abstract


This paper presents a system which asserts understanding of complex utterances by semiotic analysis. The question in the title was chosen because: it enquires about a conceptual state of affairs, referring to in two ways; and reaches an answer by subtracting I from we to get the unspoken you. The system introduces concepts, that about which we can speak, defined by repertoires in natural language, including phrasal analysis patterns. The repertoire conceptualization grounds it on a state of affairs against which reasoning can be performed. On matching an utterance, associated intentions are internally vocalized; thus, concepts are informed by more specific concepts. The repertoire conceptualism allows hypothetical states of affairs to be constructed, such as in the title question.

A Semiotic Analysis of If we are holding hands, whose hand am I holding? | Request PDF. Available from: https://www.researchgate.net/publication/285018600_A_Semiotic_Analysis_of_If_we_are_

holding_hands_whose_hand_am_I_holding.