1     Functions

Natural Language Understanding (MMC-NLU):

Receives
  1. Text Object directly input by the Entity.
  2. Recognised Text from the Automatic Speech Recognition AIM.
  3. An ID of an Instance.
  4. The Audio-Visual Scene Descriptors containing the Instance ID.
Performs The following processing:

  1. Refines the Input Text if coming from an Automatic Speech Recognition AIM
  2. Extracts Meaning (Text Descriptors) from Recognised Text or Entity’s Text Object.
Produces
  1. Refined Text.
  2. Text Descriptors (Meaning).
Enables Personal Stats Display to produce a Portable Avatar.

2      Reference Architecture

Figure 1 depicts the Reference Architecture of the Natural Language Understanding AIM.

Figure 1 – The Natural Language Understanding AIM

Note that Output Data in italic are passed directly from the homonymous Input Data.

3      I/O Data

Table 1 specifies the Input and Output Data of the Natural Language Understanding AIM.

Table 1 – I/O Data of the Natural Language Understanding AIM

Input Description
Text Object Input Text.
Recognised Text Text from the Automatic Speech Recognition AIM
Instance Identifier The Identifier of the specific Audio or Visual Object belonging to a level in the taxonomy.
AudioVisual Scene Descriptors The digital representation of the spatial arrangement of the Visual Objects of the Scene.
Visual Instance Identifier The Identifier of the specific Visual Object belonging to a level in the taxonomy.
Output Description
Meaning Descriptors of the Refined Text.
Refined Text The refined version of the Recognised Text from the NLU AIM.

4     SubAIMs

No SubAIMs.

5     JSON Metadata

https://schemas.mpai.community/MMC/V2.2/AIMs/NaturalLanguageUnderstanding.json

6    Profiles

The Profiles of the Natural Language AIM are specified.