Page History
| Excerpt |
|---|
Creates a bag of words / tfidf tag with the vector information for the document/text_block/sentence. Accumulates the vector until the engine cannot read any further |
Operates On: Lexical Items with TOKEN and possibly other flags as specified below.
Saga_is_recognizer Recognizer false
| Include Page | ||||
|---|---|---|---|---|
|
Configuration Parameters
Parameter summary JSON map resource in which the vocabulary is stored name vocabulary required true Parameter summary Type of algorithm to use then building the vector, can be either BOW or TF_IDF default BOW name vectorType required true Parameter summary Dataset ID from which the vocabulary was extracted name datasetId required true Parameter summary Minimum number of tokens to match default 1 name min type integer required true Parameter summary Maximum number of tokens to match default 2 name max type integer required true
| Saga_config_stage | ||||||||
|---|---|---|---|---|---|---|---|---|
| ||||||||
"vocabulary": "saga-provider:saga_vocabulary", "vectorType": "BOW", "datasetId": "dataset-234ifgbqafgoail3", "min": 1, "max": 3, |
Example Output
In this example the stage load a predefined vocabulary to generate a vector for the sentence using BOW, the same is done but using TF_IDF
| Saga_graph |
|---|
V---------------------------[The pilot landed safely the aircraft after gear failed when approaching the runaway.]----------------------------V
^-[The]-V-[pilot]-V-[landed]-V-[safely]-V-[the]-V-[aircraft]-V-[after]-V-[gear]-V-[failed]-V-[when]-V-[approaching]-V-[the]-V---[runaway.]----^
^-[the]-^ ^---[landed safely]---^---[the aircraft]---^---[after gear]---^---[failed when]---^---[approaching the]---^-[runaway]-V-[.]-^
^---[pilot landed]---^---[safely the]---^---[aircraft after]---^---[gear failed]---^---[when approaching]---^ ^---[runaway .]---^
^---[The pilot]---^ ^-----[the runaway.]------^
^---[the pilot]---^ ^---[the runaway]---^
^-------------------------------------------------------------------[{BOW}]-------------------------------------------------------------------^
V---------------------------[The pilot landed safely the aircraft after gear failed when approaching the runaway.]----------------------------V
^-[The]-V-[pilot]-V-[landed]-V-[safely]-V-[the]-V-[aircraft]-V-[after]-V-[gear]-V-[failed]-V-[when]-V-[approaching]-V-[the]-V---[runaway.]----^
^-[the]-^ ^---[landed safely]---^---[the aircraft]---^---[after gear]---^---[failed when]---^---[approaching the]---^-[runaway]-V-[.]-^
^---[pilot landed]---^---[safely the]---^---[aircraft after]---^---[gear failed]---^---[when approaching]---^ ^---[runaway .]---^
^---[The pilot]---^ ^-----[the runaway.]------^
^---[the pilot]---^ ^---[the runaway]---^
^-----------------------------------------------------------------[{TF_IDF}]------------------------------------------------------------------^ |
Output Flags
Lex-Item Flags:
- WEIGHT_VECTOR - Identifies the tag as a weight vector representation of a sentence
Resource Data
Description of resource.
Resource Format
| Saga_json | ||
|---|---|---|
| ||
"_id" : "KGAAJGsBemSwA0nZTLXA",
"tag": "recipe",
"pattern": "("how many"|"how much") {ingredient} ",
"confAdjust": 0.95
. . . additional fields as needed go here . . . |
| Note |
|---|
|
Fields
Parameter summary What to show the user when browsing this entity name display required true Parameter summary Tag which will identify any match in the graph, as an interpretation name tag required true These will all be added to the interpretation graph with the SEMANTIC_TAG flag.
Tip Tags are hierarchical representations of the same intent. For example, {city} → {administrative-area} → {geographical-area}
Parameter summary Pattern to match in the content name pattern required true
| Include Page | ||||
|---|---|---|---|---|
|
Overview
Content Tools