Phrase Detection

Phrase detection identifies phrases in your signals so that results with matching phrases can be boosted. This helps compensate for queries where phrases are not distinguished with quotation marks. For example, the query ipad case is rewritten as “ipad case”~10^2, meaning that if ipad and case appear within 10 characters of each other then boost the result by a factor of two.

Phrases are applied in the Text Tagger stage of the query pipeline.

The Phrase Extraction job automatically creates phrases based on your AI-generated data. When you navigate to Relevance > Query Rewriting > Phrase Detection, you can review or edit the output from the job and manually add new phrases. Your changes remain in the _query_rewrite_staging collection until you publish them.

Tip
When you manually add new phrases, subsequent job runs use those documents as input for machine learning to improve the job’s output. Unlike job-generated documents, manually-added query rewriting documents are never overwritten by new job output.

Phrase Detection screen

Reviewing auto-generated phrases

Phrases that are automatically generated by the Phrase Extraction job are assigned one of these Status values:

  • Auto

    These results have a confidence level as a threshold to automatically deploy them to the _query_rewrite collection. This threshold can be specified in the configuration parameter Minimum Likelihood Score (default value 0.1).

    No action is required on these results, though you can edit them if you wish.

  • Pending

    The confidence level is ambiguous, and the result must be reviewed by a user before it can be deployed. It will only be moved from the _query_rewrite_staging collection to the _query_rewrite collection when its status has changed to "Approved" and it has been published.

    See below for instructions.

How to review a pending phrase result
  1. Navigate to Relevance > Query Rewriting > Phrase Detection.

    Tip
    Notice the Status facet on the left. Click Pending to view only the items that need review.
  1. Click the Edit icon icon next to the phrase.

  2. In the Status column, select either "Approved" or "Denied".

    Optionally, you can also edit the phrase itself.

    Tip
    Although the Confidence field is also editable, changing its value makes no difference.
  3. Click the Close icon next to the updated phrase:

    Close a phrase

Note
Approving a phrase does not automatically deploy it to the _query_rewrite collection. When you have finished your review, you must click Publish to deploy your changes.

Adding new phrases

In addition to the phrases generated by the Phrase Extraction job, you can manually add your own.

How to add a phrase
  1. Navigate to Relevance > Query Rewriting > Phrase Detection.

  2. At the bottom of the rules list, click the Add icon icon.

    A new phrase appears at the top of the list:

    Add a phrase

  3. Enter the phrase.

    Tip
    It’s not necessary to set a confidence value.
  4. Select the phrase’s status, depending on whether you want to deploy it the next time you publish your changes ("Approved") or save it for further review ("Pending").

  5. Click the check mark to save the new phrase:

    Save a phrase

Publishing your changes

How to publish updated phrases
  1. In the Phrase Detection screen, click the PUBLISH button.

    Fusion prompts you to confirm that you want to publish your changes.

  2. Click PUBLISH.

Tip
You can un-publish a query rewrite by changing its status to "pending" or "denied", then clicking PUBLISH.