You are viewing an old version of this page. View the current version.
Compare with Current
View Page History
« Previous
Version 2
Next »
This recognizer uses a frozen Universal Sentence Encoder Tensorflow model to encode, using sentence embedding vectors, a list of Frequently Asked Questions and tag sentences that match a question/answer pair given a specified threshold of accuracy with the question/answer from the FAQ.
Before adding the FAQ Recognizer, download the tensorflow model from here and unzip it under %SAGA_SERVER%\tf-models
Configuration
![](/download/attachments/808388828/image2019-6-7_10-38-57.png?version=1&modificationDate=1559931288000&api=v2)
-
Match threshold ( type=double
| default=0.8
| required
)
- The minimum similarity match between the vectors of a sentence and a question/answer to consider the question to tag the input sentence.
-
Eval Answer ( type=boolean
| default=false
| required
)
- Whether or not to include the answer vectors when evaluating an input sentence.
Adding a Question/Answer pair
By clicking in the
which will popup the Add new FAQ dialog
-
Write question here ( type=string
| required
)
- Question to add to the FAQ
-
Write answer here ( type=string
| required
)
- Answer to the question
-
Url ( type=string
| optional
)
- If provided, the source of the question/answer. (Usually a link to the HTML FAQ page).
-
Confidence Adjustment ( type=double
| default=1
| required
)
- Confidence Adjustment for this entry
- 0.0 to < 1.0 decreases confidence value
- 1.0 confidence value remains the same
- > 1.0 to 2.0 increases confidence value
![](/download/attachments/808388828/image2019-6-7_10-52-46.png?version=1&modificationDate=1559931288000&api=v2)
Load FAQ for evaluation
Clicking on the
will encode all question/answer pairs for evaluations.
When
show in orange means that the vectors have been loaded and its ready to use for matches.
Click on
to copy the sentence embedding vector of the question (top) or answer (bottom) for debugging purposes.
General Settings
The general settings can be accessed by clicking on
![](/download/thumbnails/808388856/image-2023-8-7_9-7-27.png?version=1&modificationDate=1691420847668&api=v2)
![](/download/attachments/808388856/image-2023-8-7_9-5-29.png?version=1&modificationDate=1691420729124&api=v2)
- Enable - Enable the processor to be use in pipelines.
- Base Pipeline - Indicates the last stage, from a pipeline, needed by the recognizer.
- 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 Flag ( optional ) - Lexical items flags needed by every token 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.