Build Intuit

Reference Frames & Artificial General Intelligence

“To understand is to experience harmony between what we aim at and what is given, between the intention and the performance – and the body is our anchorage in the world. ”  ―  Maurice Merleau-Ponty

A Resource Project for Natural Language Processing

Site Summary: There are countless scenarios that humans can recognize and machines cannot. To enhance machine awareness of commonsense concepts, the idea is to analyze the words of a text utilizing reference frames. We call it word-sensibility. The goal is a text analysis to assess word sense by simulating human responsiveness. That is, the ability to act quickly and positively to situations in the world. Reference frames move quickly between general and relevant viewpoints. In this way, machines can make better sense of the many things that people typically know. A conceptual model and propositions are proposed that could form the basis for further research.

The Quadranym Model of Word-Sensibility (Q): An Ecological System Perspective On Word-Level Concepts and Dynamical Contexts — Non-Mental-Representation Representation — Action Based Theory of Context.

Q System: A method to analyze and cluster words – an ontology alignment system to represent dynamic word sense relations in units, scripts and layers.


Brief Introduction

Word-Sensibility is a theoretical approach that can be interpreted for a wide variety of applications (e.g.,  API services for NLP and metaphor-analysis).

The general approach is most concerned with the non-linguistic aspects of using language, aspects that ground the responsiveness of communication.

Normative Responses for Artificial Intelligence:

Word-Sensibility is proposed as a model for text analysis. Data training involves a database with its features tagged to identify apt reference frames

Consider the sentence: “Let’s move the couch over there.”

General reference frames aptly apply, such as: agent, energy, time and space.

Reference Frames anchor on word states that target topic variables:

  • If agent: then self targets goal to find ‘agent’ topic variables.
  • If time: then present targets event to find ‘time’ topic variables.
  • If space: then void targets between to find ‘space’ topic variables.
  • If energy: then motion targets matter to find ‘energy’ topic variables.

The relevant response is about why people move furniture around. The general response is about intuitive grounding and orientation. The aim is to create Systems of Orientation by layering frames and repurpose the systems.

  • Orientation for the sentence example is a From self To matter system.

Frames utilize mode variables so they can adjust target coordinates on the x-y axes to coordinates that the orientation can most effectively anchor for.

Orient Energy: Self, Motion = Active(move) > Goal, Matter = Passive(couch).

Above represents energy layers. The left frame anchors on the energy of the agents. The right frame anchors on the left frame with apt modes on couch.

  • Mode variables: y active/x passive, y size/x weight

Reference frames nest into various hierarchical layers (i.e., from general to relevant). These nested layers form virtual systems of responsiveness. The approach aims to assist with hard Artificial General Intelligence (AGI) tasks.

Such as:

(Developing a viable Q system requires a Neuro-Symbolic (hybrid AI) approach.)

Visit the About page for the project’s motivation, scope and goals.  We are in the exploratory stage and look forward to any feedback. Please Contact.


The General Approach 
Above From: About Page.

Eros & Psyche
Movement Toward the Whole of Relatedness with All the Processes of Mind (sec. C Jung)

About

Model

Contact

        Drafts - Work In Progress - Do Not Quote Or Distribute

© 2018 buildintuit.com All Rights Reserved