Build Intuit

A Resource Project for Natural Language Processing

“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

Reference Frames & Artificial General Intelligence

Site Summary: Machines can’t acquire commonsense naturally as humans do. To assist the machine acquisition 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 learn to make better sense of the 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 Psychology Perspective on Word-Level Concepts and Situational ContextsNon-Mental-Representation Representation — Action Based Theory of Context.

Q System: Semantic word relations represented in units, scripts & layers.

Visit the About page for the project’s motivation, scope, goals and theory. 

Model Overview

Context isn’t just the surrounding circumstances, because it includes and interacts with the subject that is surrounded, and the agent that tries to comprehend it all. ― Andrew Hinton 🔗

  1. Introduction
  2. Reference Frames
  3. Systems of Orientation
  4. Services to Assist Orientation
  5. Reference Frame Models
  6. Q Scripts and Layers
  7. Q System Database
  8. Theory Summary
  9. Summing-up
1. Introduction

Word-Sensibility is About Agents Orienting to Communications:

In this overview, we’ll introduce, reference frames, dynamical contexts and quadranyms. These features aim to represent the responsiveness of agents. 

  • Goal: Improve commonsense prediction with units of responsiveness.

Word-Sensibility is a theoretical approach that can be interpreted for a wide span of applications: from  API services for NLP to metaphor-analysis.

The theoretical ideas are most concerned with the non-linguistic aspects of using language, aspects that ground the responsiveness of communication.

(Note: The overlap between various semantic categories with sensory motor areas suggests that a common mechanism is used by neurons to process action, perception and semantics. Body & environment play important roles in thinking.)

2. Reference Frames

Normative Responses for Artificial Intelligence:

Word-Sensibility (Q) 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.

The words of the sentence are matched to reference frames:

  • Agent(let’s), Energy(move), Time(the_couch), Space(over_there).

A reference frame (RF) is represented as a predicate for a word or subject.

For example, Let’s is the subject of Agent. let’s is predicated on Agent. 

  • A reference frame is a distinct general topic.
  • The sentence is the relevant topic or situation.
  • Each reference frame has distinct topic variables.
  • Words of text become variables of reference frames (RF).
  • RF predicates and subjects are different from sentential types.
  • Reference frame contents are called latent topic variables.

The Layered Word Order:

  1. Agent(let’s) ………….Reference Frame Topic:[<find> goal of agent]
  2. Energy(move) ………Reference Frame Topic:[<find> matter of energy]
  3. Time(the_couch) …..Reference Frame Topic:[<find> event of time]
  4. Space(over_there) …Reference Frame Topic:[<find> between of space]

Above, words of the sentence are associated with latent topic variables.

(Note: Reference frames are general semantic orientations to topic fields. They assist semantic perspectives by providing virtual orientation for the given text.)

System Report:

  • Constituents: {<let’s, move, the_couch, over_there>}.
  • The Relevant Topic (Sentence): Move(the_couch, we)
  • The General Viewpoint (Unit): Agent <find> Goal
  • Hierarchical Range (Layers): From Agent To Energy

A hierarchical system is rendered to nest words with latent topic variables.

  1. General Unit
  2. Orient Unit(s)
  3. Relevant Unit

Hierarchical Layers: From General Unit To Relevant Unit:

The number of orient units between general and relevant units can vary. 

  • The middle layers are varying degrees of relevant and general.

Layers and Units represent two dimensions for targeting relevant topics.

  • 3d Hyper RF: General layered systems can target relevant layered systems.

(Note; A nested hierarchical system prevents the lower layers from referencing the higher layers. For instance, it may be helpful to imagine nested Russian dolls,  each doll can reference the dolls it contains but not the dolls that may contain it.)

Latent Topic Variables:

Reference frames anchor on topic-states that target topic variables.

The Layered Reference Frame Order (i.e. hierarchy):

  1. If Agent: Then self targets goal to <find> ‘agent’ topic variables.
  2. If Time: Then present targets event to <find> ‘time’ topic variables.
  3. If Space: Then void targets between to <find> ‘space’ topic variables.
  4. If Energy: Then motion targets matter to <find> ‘energy’ topic variables.

(Note: Reference frames are populated by quadranyms.  See: A quadranym is the basic unit of a faceted classification scheme (Q). Any topic is analyzed into its component parts beginning with the prime quadranym classes.)

Source and Target Conditions: 

To understand text humans share some basic knowledge about the world.  The reader intuits the general conditions when given the relevant context.  

  • Relevant Context: Move(the_couch, we) 

(Note: let’s = argument (allow, we); subject; first person plural imperative.)

General Topic Conditions: 

  • Agent: self goal
  • Time: present event
  • Space: void between
  • Energy: motion matter

The source conditions (i.e., anchor states) are self, present, void and motion. The target conditions (i.e., target states) are goal, event, between and matter.

  • Generic Condition States: source target

For example, consider the two condition states for the word-topic Space:

  • Space: voidbetween 

In this reference frame example, the anchor void targets between to find apt spatial measures such as, objects, regions, solid separation & spatial separation.

  • Void is a factor that is a constant in relation to any variable of between. Void is in essence the background in a figure-ground relationship with between

Source and target conditions are virtual mental states. Situations occur in the world. A source relies on a target to find what’s relevant in a situation.  

  • A source condition is unmeasured. So, a target is required to find measure. 

In theory, a source is needed for frames to elicit potential target conditions. The idea is straightforward, there can be no foreground without background.

  • The invariable source is the standpoint taken. Topic variables are the target. 

(Note: Source and target conditions borrow and abstract from James Gibson: Perception is the process of selecting, organizing, and interpreting information from our senses. Selection: Focusing attention on certain sights, sounds, tastes, touches, or smells in your environment. Something that seems especially noticeable and significant is considered salient. Organization: Taking the information selected and organizing it into a coherent pattern in your mind. Structuring the information you have selected into a chronological sequence that matches how you experienced the order of events is known as punctuation. Interpretation: Assigning meaning to the information you selected by calling to mind relevant, familiar information to make sense of what you are hearing/seeing; source & target conditions refer to subsequent semantic process.)

The aim is a system to bridge between subjective and objective ontologies.

  •  Duel Ontology(has reciprocal relationships): Subjective ⇆ Objective  

(Note: Implies, virtual sensory motor-systems coupling with semantic orienters.)

Reference frames provide actual orientation and potential topic targets.

  • Subjective: general source condition ➝ Objective: relevant target condition
  • Source conditions refer to the intersubjective construction of communication.
  • Target conditions refer to the objective relations that provide understanding. 

(Note: Q subjectives primarily imply organismic conditions — then opinions. If a reference frame does not pull relevant context then change the reference frame.)

As one more example, say there is Energy. In the Energy frame, the source condition is motion. What makes it relevant to a situation is the matter of Energy. For instance, if something is falling on Pat, falling being motion, then relevant is what’s falling as matter  e.g., raindrops vs. a piano is relevant.

(Note: Source & target conditions are semantic orienters for situational contexts. A quadranym has a subjective state or source condition and an objective state or target condition.  We introduce quadranyms in section 8. Q System Database.)   

Condition Classes & Domain Classes:

Source and target conditions are subsets of source and target domains.

  • Conditions ⊂ Domains 

Theoretically, conditions and domains develop on the same continuum and become distinct over time. Conditions become domains and prove the logic.

  • In the system, conditions are considered transient while domains are steady. 

(Note: Source and target conditions are held between ‘mental domains’. Domains such as social and spatial can share conditions e.g. In the club = self ➝ between. Progression: conditions form references which form realms which form domains. Realms are random reference classes and domains are ordered reference classes. •You might say that the realm is more fungible while the domain is less fungible.)

3. Systems Of Orientation

Relevant Responses Require General Responses to Anchor On:

Let’s look at how the words of the text are parsed to layers as source and target conditions. A word takes on different roles depending on the layer.

Again, consider our example: Let’s move the couch over there.

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 ― scripts form on layers.

  • Systems of orientation combine, modify and layer reference frames together.

The system works to engage states e.g., agents in a temporal sequence, in a space, using energy. The sentential content is parsed to source and targets

  • e.g., the_couch can be either a source or target depending on the layer.

The words of a text are represented as subjects predicated on topic-states:

  1. From General: Agent: source Self(let’s) target Goal(move).
  2. Orient: Time: source Present(the_couch) target Event(move)
  3. Orient: Space: source Void(move) target Between(over_there)
  4. To Relevant: Energy: source Motion(move) target Matter(the_couch).

Above represents a nested hierarchy with layered viewpoints. Notice that the_couch and move are represented as both, targets and source conditions.

  • the_ couch is what’s at present in Time and is also the matter of Energy.
  • The base verb move is aptly assigned condition states for each layer.

move: Base Verb & State Conditions:

  1. move relatedTo Agent = goal as target condition 
  2. move relatedTo Time =  event as target condition 
  3. move relatedTo Space = void as source condition 
  4. move relatedTo Energy = motion as source condition

Move (verb of the sentence) has the most basic relation relatedTo for each condition. More specific relations such as, move isA goal or event can be set.

(Note: Knowledge graphs assign relations. See: Services to Assist Orientation.)

Below, is a description of the representation for the rest of the sentence.

the_couch: Direct Object & State Conditions: 

  • The general source condition of Time is present or present-at-hand.
  • the_couch is present-at-hand and targets its topic variable move.
  • Also, the_couch is the relevant condition of the most relevant unit.
  • Energy is the most relevant unit where motion (move) targets matter.

over_there: Prepositional Phrase & State Condition:

  • The general source condition of Space is void or empty.
  • Unobstructed is a source condition with spatial movement.
  • objects and regions are target variables of spatial movement.
  • The prepositional phrase over_there infers objects and regions.

let’s: Imperative Verb & State Condition:

  • The general condition of Agent is self.
  • Self is a source condition with let’s (we, allow).
  • Selves is the primary assumption for other(s) or we.
  • Imperative verb Let’s is Self targeting the Goal move

The words of the sentence are conditioned to the situational context.

(Note: The syntax of a sentence helps assign words conditions. See next section)

4. Services to Assist Orientation

Network Systems Situate the Words of a Text to Reference Frames:

Neural network deep learning methods cluster words in reference frames.

  • Word associations acquired with word embeddings can receive orientations.

Corpora, Networks & Knowledge Graphs:

Services to help link situational categories (networks) are available such as, WordNet semantic relations and ConceptNet commonsense knowledge graphs.

The topic states have synonymic relations e.g., void > vacant > unobstructed. This and knowledge graphs can align states to a situation e.g., move isA goal

Conditions of a reference frame adjust to the topic or situational context:

  1. Agent:  move isA goal  
  2. Time:    move isA event  
  3. Space:   move hasPrerequisite unobstructed  
  4. Energy: move isA motion  

(Note: Above, each reference frame gives ‘move’ a unique dynamical context. We introduce the dynamical context in the next section: 5. Reference Frame Models.)

Grammar Links for Source and Target Conditions:

Word-sensibility uses syntactic analysis when parsing words to reference frames.  Syntax assists finding, grouping or conjoining words for placement.

Syntactic Analysis see: Link Grammar (API)

    |                     +-------MVp-------+        |
    |       +------I------+----Os----+      |        |
    +---Wi--+--Op--+      |    +--Ds-+      +--J-+   |
    |       |      |      |    |     |      |    |   |
LEFT-WALL let.v s[!].n move.v the couch.n over there . 

Constituent tree:

(S (VP Let [Contraction let's]
       (NP s )[Pronoun Phrase us]
       (VP move
           (NP the couch)
           (PP over
               (NP there))))

D connects determiners to nouns.
J connects prepositions to their objects.
I connects certain verbs with infinitives
O connects transitive verbs to direct or indirect objects.

Relations between frames and syntax add a potential level of predictivity.

Each layer has an anchor, target and grammar links

  1. Agent: let’s ➝  move: From imperative verb To infinitive (base) verb (I). 
  2. Time: the_couch ➝  move: From direct object To transitive verb (O). 
  3. Space: move ➝  over_there: From verb To prepositional phrase (MV). 
  4. Energy: move ➝  the_couch:  From transitive verb To direct object (O).

Words of Text Become New Anchors for New Sets of Target Variables:

The system identifies new topic variables for new source conditions.

  •  New Anchor: Let’s ➝ target variables < Agent

In the example, the relation relevant to the situation is;  If let’s Then move. Let’s is the anchor and is a constant. Move is the target variable. It could be, If let’s Then try, sit or eat, or whatever becomes relevant to a given situation.

  • The aim is to amass clusters of target variables for each anchored frame.
  • The target variables available to a frame are based on the given situation.

(Note: Quadranym renderings utilize a neural net and Q system hybrid.)

5. Reference Frame Models 

Word-Sensibility Proposes Two Complimentary Systems of Context:

The Situational Context is predicated on Move(the_couch, we). We introduce the Dynamical Context*.   It’s about responsive alignment to the situation.

  • Words (text data) cluster in reference frames becoming situational variables.
  • Content collected in each reference frame has a specific Dynamical Context.

*(Note: The dynamic context communicates the changes in a situation while the dynamical context communicates a system’s response to changes in a situation.)

The Dynamical Context Couples with The Situational Context.

Source Condition: motion ➝ Target Condition: matter

The images above are reference frame models for Energy. The images show different sets of mode-variables. Modes align target states to the situation:

Mode Variables:

  1. Left Image) Modes:passive x, active y
  2. Right Image) Modes: weight x, size y


  1. left: general, active-passive, calibrate to situation [move ➝ matter ].
  2. right: relevant, size-weight, calibrate to matter [move ➝ the_couch].

The more-general left frame cues a mean for how much weight people can move. The more-relevant right frame cues a mean for the weight of couches.

  • General: How much the average person can lift, slide or budge.
  • Relevant: Average weight of something e.g., couch, vase or mountain.

Situational Alignments: (Virtually aligning the agent to the world.)

Below, the content is parsed into the more-general reference frame.

:[Active(motion:(y=Let’s, move, over_there)) ⊇ Passive(matter:(x=the_couch))]

  • Modes and Causal Relations: dependent y and independent x 

Alignment depends on situational variables e.g., xcouch, xvase or xmountain.

  • Modes are used in regression analyses to compare and select target variables.

To anchor the energy topic to any situation, active is dependent on passive. A more relevant set of mode-variables (size & weight) target the X(?…couch).

:[Size(motion:(y=move )) ⊇ Weight(matter:(x=the_couch))]

In terms of Energy, moving something of any size depends on its weight.

This is one example. The calibration can be utilized in different ways. Also, other reference frames can be aptly nested in such as, distance or direction.

(Note: Target variables are organized in scripts. see next section.) 

6. Q Scripts and Layers

Scripts are on the Horizontal and Layers are on the Vertical in the Matrix:

We’ll just touch on some basic ways to think about scripts and layers.

Basically, layers are more logarithmic and scripts are more linear. Or,  you might say that layers are more heuristic and scripts are more deliberative.

  1. Layers: agent:[Y(self) ⊇ X(goal)]<over> energy:[Y(motion) ⊇ X(matter)]
  2. Script: energy:[Y(motion) ⊇ X(matter)]<find>[Y(matter) ⊇ X(?… couch)]

Notice the quick links; self is layered over motion and goal over matter

(Note: quick links like goal <isRelatedTo> matter is based on quadranym matrix.)

The y variable is about potential active relations between the agent and the world. The x variable is about a thing being acted upon (x thingifies anything).

In scripts, targets become anchors for the next frame.

  • Content iterates through a script until the cycle is complete. 
  • New reference frames are constructed through the process.

Scripts are meant to run on different layers and at different cycles. In theory,  the more general a script is the less cycles it will need to run.

(Note: A script is an iteration process: cycle source and target conditions.)

7. Q System Database

1) Quadranym Database:

Quadranyms populate reference frames.

  • The quadranym is the smallest unit of context in the Q system.

 2) Quadranyms:

Quadranym example: energy: (Semantic Set = Four Dimensions)

  • Active, Passive, Matter, Motion

3) Quadranym Representation: (Semantic Set Variable)

  • (x)  energy(x)  [Active(motion Passive(matter)(x)] 

An Alternate Semantic Set Resource Variable: (it’s like a word sense)

  • Alt e.g., (x)  energy(x) [Available(power Deplete(fuel)(x)]

4) Phrase Template: (Orient Semantic Unit with Mode-Variables)

Anchor (general): For the motion of Energy;

Target (relevant):

  1. Active is Dependent on Passive to Find matter
  2. Work is Dependent on Power to Find matter
  3. Size is Dependent on Weight to Find matter

5) Generic Quadranym Dimensions or Primes:

A quadranym is the basic unit of a faceted classification scheme. Any topic is analyzed into its component parts beginning with the prime quadranym unit

Prime Unit: Expansiveness, Reductiveness, Objectiveness, Subjectiveness

  • Mode Primes: Expansive adj, Expand v, (-,+) ⊇ Reductive adj, Reduce v, (+,-)
  • State Primes: Subjective adj, Subject n,  (-,-) ⊇ Objective adj, Object n,  (+,+)

Quadranyms can be structured in a free form design or alternatively into a conjugal design,  where a state is always a noun and mode is always a verb.

  • Topic: Transfer:[E = move v, R = put v, O =  location n, = S Item n]
  • (x)  transfer(x) [Move(item Put(location)(x)] < energy realm

Basic Quadranym Phrase Template: 

The generic phrase template form: FOR the subjectiveness of any-topic; expansiveness is DEPENDENT on reductiveness to FIND objectiveness.

See:  (Database • Acquisition • Wiki)

8. Theory Summary

Word-Sensibility Hypothesis: 

The agent accumulates actual dynamic sense through experience and will act upon the dynamic sense necessary to orient to a given communication.

Orienting to Text (so to narrow relevant topic variable options):

  • Situational sense is the potential sense of one’s actual dynamic sense.
  • Dynamic sense can be literally or figuratively matched to a situation.

Two distinct systems of context adds stability and versatility for analysis.

  • The situational context is about truth conditions (less fungible).
  • The dynamical context is about responsiveness (more fungible).

Dynamical contexts have no value unless coupled to situational contexts. Situational contexts need dynamical contexts to communicate orientation.

  • There is a reciprocal kind of relationship between the two systems of context.

A reference frame is like a bias that allows assumptions about topics. This includes generalizations where conditions between domains are compared.

  • The orienting example may apply to other situations e.g., reaching or passing.
  • The system orients for prediction conditions and counterfactual conditions. 
  • Systems of orientation can be repurposed to orient metaphoric conditions.

Metaphoric Condition: “Moving that little couch was like moving a mountain.”

See the slideshow for more info: The Dynamical Context (bottom of page)

Agents: We see the agent as a system in an ecological relationship with its environment. For a helpful view of agents in general see: Multi-Agent Systems.

(Note: There is no actual subjective and objective distinction in Q hierarchical structures. Mental attributes and environmental attributes are nested layers in a single global system. The distinction is in quadranyms and is temporal and local.)

9. Summing-Up

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:

Ultimately, the goal is to enable machines the ability to share viewpoints.

  • Topic interoperability is the ability to adopt or reject the topic orientations of other AI systems. Competitive performance comparisons advance schemes.

    Q system reference frames can be used with deep learning models, that utilize word embedding methods,  to orient the word associations learned. 

    • Developing a Q system requires a Neuro-Symbolic (hybrid AI) approach.
    • Data components: database, knowledge graphs, ontology and open text.

    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.

    Introducing The Dynamical Context 
    Above From: About Page.

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




            Drafts - Work In Progress - Do Not Quote Or Distribute

    © 2018 All Rights Reserved