Connects directly to the Python Bridge, to send text or sections of the interpretation graph to be process by ML algorithms in Python

Uses Python Model Stage

Configuration

  • Service Hostname ( type=string | default=localhost | required ) - Python server communication hostname
  • Service Port ( type=integer | default=5000 | required ) - Python server communication port
  • Select Model ( type=string | default=lsi | required ) - Model name registered in the python bridge
  • Select Version ( type=string | required ) - Model version registered in the python wrapper to query
  • Service Model Method ( type=string | required ) - Model method to call for the model

Settings

  • Normalize Tags (optional) - Tags (flagged as SEMANTIC_TAG) are normalized. Whenever a tag has field (metadata) named "display" it value is used to normalize the tag, if the tag does not have "display" value then the name of tag is used, e.g. {costumer} = costumer.

  • Include Context (optional) - Includes up to two fields in the metadata of the new tag, the values are "before" and "after". The "before" value includes previous blocks (or lines) from the current text being process, using the "Boundary Flags" from the general settings to delimit the blocks, existing in the current graph, up to 2 blocks if possible. The "after" field include up to two blocks after the processed text.

  • Skip Vertex Flags (optional) - List of flags used to skip blocks (or lines) that should not be process by the stage.  The flagged vertex marks the start of the block and the end is set by the "Boundary Flags" value in the settings.

General Settings

The general settings can be accessed by clicking on 


  • Enable - Enables the processor to be used in the pipeline.
  • Skip Flags ( optional ) - Lexical items flags to be ignored by this processor.
  • Boundary Flags  ( optional ) - List of vertex flags that indicate the beginning and end of a text block.
  • Required Flags ( optional ) - Lexical items flags required by every token to be processed.
  • At Least One Flags ( optional ) - List of lexical item flags where at least one of them needs to be present to be processed.
  • Don't Process Flags ( optional ) - List of lexical items flags that are not processed. The difference with "Skip Flags" is that this will drop the path in the Saga graph, skip just skips the token and continues in the same path.
  • Confidence Adjustment - Adjustment factor to apply to the confidence value of 0.0 to 2.0 from (Applies for every match).
    • 0.0 to < 1.0  decreases confidence value
    • 1.0 confidence value remains the same
    • > 1.0 to  2.0 increases confidence value
  • Debug - Enable debug logging.

  • No labels