Fragmentation Stage

Identifies patterns with a combination of any number of specified tokens, regardless of the tokens it may be in between

Operates On: Lexical Items with TOKEN or SEMANTIC_TAG and possibly other flags as specified below.

Configuration Parameters

patterns (string, required) - The resource which contains the pattern database
- See below for the format.
boundaryFlags (string, optional)
- The tokens to process must be inside two vertex mark with this flags (e.g ["TEXT_BLOCK_SPLIT"])
skipFlags (string array, optional) - Flags to be skipped by this stage
- Tokens marked with this flags will be ignore by this stage, and no process will be performed.
requiredFlags (string array, optional)
- Tokens need to have all the specified flags, in order to be processed
debug (boolean, optional)
- Enable all debug log functionality of the stage, if any.

Example Configuration

{
 "type":"Fragmentation",
 "patameter":"fragmented-provider:patterns",
 "boundaryFlags":["TEXT_BLOCK_SPLIT"]
}

Example Output

Description

V--------------[abraham lincoln likes macaroni and cheese]--------------------V
^--[abraham]--V--[lincoln]--V--[likes]--V--[macaroni]--V--[and]--V--[cheese]--^
              ^---{place}---^           ^----{food}----^         ^---{food}---^
^----------{person}---------^           ^-----------------{food}--------------^

Output Flags

Lex-Item Flags:

SEMANTIC_TAG - Identifies all lexical items which are semantic tags.
FRAGMENT- Identifies all lexical items which were created from a fragmentation pattern.
PROCESSED - Placed on all the tokens which composed the semantic tag.

Vertex Flags:

none

Resource Data

The resource data will be a database of fragmented patterns, and the resulting semantic tag which they produce.

Resource Format

The only file which is absolutely required is the entity dictionary. It is a series of JSON records, typically indexed by entity ID.

Description of entity:
Entity JSON Format

Entity JSON Format

{
  "id":"Q28260",
  "tags":["{city}", "{administrative-area}", "{geography}"],
  "patterns":[
    "Lincoln", "Lincoln, Nebraska", "Lincoln, NE"
  ],
  "options": {
	"minTokens": 3,
    "maxTokens": 6,
    "combination": true
  }
  "confidence":0.95
  
  . . . additional fields as needed go here . . . 
}

Notes

Multiple entities can have the same pattern.
1. If the pattern is matched, then it will be tagged with multiple (ambiguous) entity IDs.
Additional fielded data can be added to the record
1. As needed by downstream processes.

Fields

id (required, string) - Identifies the entity by unique ID. This identifier must be unique across all entities (across all dictionaries).
- Typically this is an identifier with meaning to the larger application which is using the Language Processing Toolkit.
tags (required, array of string) - The list of semantic tags which will be added to the interpretation graph whenever any of the patterns are matched.
- These will all be added to the interpretation graph with the SEMANTIC_TAG flag.
- Typically, multiple tags are hierarchical representations of the same intent. For example, {city} → {administrative-area} → {geographical-area}
patterns (required, array of string) - A list of patterns to match in the content.
- Patterns will be tokenized and there may be multiple variations which can match.
  - NOTE: Currenty, tokens are separated on simple white-space and punctuation, and then reduced to lowercase.
  - TODO: This will need to be improved in the future, perhaps by specifying a pipeline to perform the tokenization and to allow for multiple variations.
options (optional, JSON Object) - Object with options applicable for this entity
- minTokens (optional, int) - Minimum number of tokens the match must contains to be valid, default is the number of tokens each pattern has
- maxTokens (optional, int) - Maximum number of tokens the match must contains to be valid, default is the number of tokens each pattern has
- combination (optional, boolean) - Indicates if the given tokens can be match in any order possible as long all appear in the match, if false, it means the tokens need be in the order provided
confidence (optional, float) - Specifies the confidence level of the entity, independent of any patterns matched.
- This is the confidence of the entity, in comparison to all of the other entities. Essentially, the likelihood that this entity will be randomly encountered.

Other, Optional Fields

display (optional, string) - What to show the user when browsing this entity.

Page tree