Skip to main content
Use this job to generate pairs of synonyms and pairs of similar queries. Two words are considered potential synonyms when they are used in a similar context in similar queries.
This job is deprecated in Fusion 5.9.15 and will be removed in a future release. Lucidworks recommends migrating to Neural Hybrid Search, which achieves superior relevance compared to legacy machine learning methods.
LucidAcademyLucidworks offers free training to help you get started.The Course for Resolving Underperforming Queries focuses on tips for tuning, running, and cleaning up Fusion’s query rewrite jobs:
Resolving Underperforming QueriesPlay Button
Visit the LucidAcademy to see the full training catalog.
Default job nameCOLLECTION_NAME_synonym_detection
Input
● Aggregated signals (the COLLECTION_NAME_signals_aggr collection by default)
● Spell Correction job output (the COLLECTION_NAME_query_rewrite_staging collection by default)
● Phrase Extraction job output (the COLLECTION_NAME_query_rewrite_staging collection by default)
OutputSynonyms (the COLLECTION_NAME_query_rewrite_staging collection by default)
querycount_itypetimestamp_tdtuser_iddoc_idsession_idfusion_query_id
Required signals fields:✅✅✅✅
For best job speed and to avoid memory issues, use aggregated signals instead of raw signals as input for this job.
Output from the Token and Phrase Spell Correction job and the Phrase Extraction job can be used as input for this job. To:
  • Review, edit, deploy, or delete output from this job, see Query Rewriting UI
  • Review, edit, or add synonyms, see Use Synonym Detection
Based on the release, synonyms are automatically created based on your AI-generated data. When you navigate to Relevance > Rules > Rewrite and select the Synonym tab, the application displays the Synonym Detection screen. For more information, see:
When you manually add new synonym pairs, 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.
Synonym Detection screen
LucidAcademyLucidworks offers free training to help you get started.The Course for Query Analytics focuses on how Fusion provides query analytics to detect and improve underperforming queries:
Query AnalyticsPlay Button
Visit the LucidAcademy to see the full training catalog.

​
Reviewing auto-generated synonym pairs

Synonyms that are automatically generated by the Fusion 5.2.x and later Synonym Detection job are assigned the following status value:
  • 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.
    By default, all results from a synonym job are set to “Pending”, since there are usually a limited number of synonyms, and synonym expansion can have high impact on relevancy.

​
How to review a pending synonym pair result

  1. Navigate to Relevance > Rules > Rewrite.
  2. Select Synonym tab. The application displays the Synonym Detection screen.
    Notice the Status facet on the left. Click Pending to view only the items that need review.
  3. Click the Edit icon icon next to the synonym pair.
  4. In the Status column, select either “Approved” or “Denied”. Where alternative synonyms were detected, you can click Suggestions to view and select them as replacements for the displayed synonym pair.
    Although the Confidence field is also editable, changing its value makes no difference.
  5. Click the Close icon next to the updated synonym pair: Close a synonym pair
Approving a synonym pair 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 synonym pairs

You can manually add synonym pairs in addition to any generated by your Fusion release:

​
How to add a synonym pair

  1. Navigate to Relevance > Rules > Rewrite.
  2. Select Synonym tab. The application displays the Synonym Detection screen.
  3. At the bottom of the rules list, click the Add icon icon. A new synonym pair appears at the top of the list.
  4. Enter the query term.
    It is not necessary to set a confidence value.
  5. Select the synonym pair’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”).
  6. Click the check mark to save the new synonym pair.

​
Publishing your changes

​
How to publish updated synonym pairs

  1. In the Synonym Detection screen, click the PUBLISH button. Fusion prompts you to confirm that you want to publish your changes.
  2. Click PUBLISH.
You can un-publish a query rewrite by changing its status to “denied”, then clicking PUBLISH.

​
Input

This job takes one or more of the following as input:

​
Signal data

This input is required; additional input is optional. Signal data can be either raw or aggregated. The job runs faster using aggregated signals. When raw signals are used as input, this job performs the aggregation. Use the trainingCollection/Input Collection parameter to specify the collection that contains the signal data.

​
Misspelling job results

Token and Phrase Spell Correction job results can be used to avoid finding mainly misspellings, or mixing synonyms with misspellings. Use the misspellingCollection/Misspelling Job Result Collection parameter to specify the collection that contains these results.

​
Phrase detection job results

Phrase Extraction job results can be used to find synonyms with multiple tokens, such as “lithium ion” and “ion battery”. Use the keyPhraseCollection/Phrase Extraction Job Result Collection parameter to specify the collection that contains these results.

​
Keywords

A keywords list in the blob store can serve as a blacklist to prevent common attributes from being identified as potential synonyms. The list can include common attributes such as color, brand, material, and so on. For example, by including color attributes you can prevent “red” and “blue” from being identified as synonyms due to their appearance in similar queries such as “red bike” and “blue bike”. The keywords file is in CSV format with two fields: keyword and type. You can add your custom keywords list here with the type value “stopwords”. An example file is shown below: 
keyword,type
cu,stopword
ft,stopword
mil,stopword
watt,stopword
wat,stopword
foot,stopword
feet,stopword
gal,stopword
unit,stopword
lb,stopword
wt,stopword
cc,stopword
cm,stopword
kg,stopword
km,stopword
oz,stopword
nm,stopword
qt,stopword
sale,stopword
on sale,stopword
for sale,stopword
clearance,stopword
gb,stopword
gig,stopword
color,stopword
blue,stopword
white,stopword
black,stopword
ivory,stopword
grey,stopword
brown,stopword
silver,stopword
light blue,stopword
light ivory,stopword
light grey,stopword
light brown,stopword
light silver,stopword
light green,stopword
Use the keywordsBlobName/Keywords Blob Store parameter to specify the name of the blob that contains this list.

​
Custom Synonyms

For some deployments, there might be a need to use existing synonym definitions. You can import existing synonyms into the Synonym Detection Jobs as a text file. Upload your synonyms text file to the blob store and reference that file when creating the job.

​
Output

The output collection contains two tables distinguished by the doc_type field.

​
The similar queries table

If query leads to clicks on documents 1, 2, 3, and 4, and similar_query leads to clicks on documents 2, 3, 4, and 5, then there is sufficient overlap between the two queries to consider them similar. A statistic is constructed to compute similarities based on overlap counts and query counts. The resulting table consists of documents whose doc_type value is “query_rewrite” and type value is “simq”. The similar queries table contains similar query pairs with these fields:
queryThe first half of the two-query pair.
similar_queryThe second half of the two-query pair.
similarityA score between 0 and 1 indicating how similar the two queries are. All similarity values are greater than or equal to the configured Query Similarity Threshold to ensure that only high-similarity queries are kept and used as input to find synonyms.
query_countThe number of clicks received by the query_count query. To save computation time, only queries with at least as many clicks as the configured Query Clicks Threshold parameter are kept and used as input to find synonyms.
similar_query_countThe number of clicks received by the similar_query_count query.

​
The synonyms table

The synonyms table consists of documents whose doc_type value is “query_rewrite” and type value is “synonym”:
surface_formThe first half of the two-synonym pair.
synonymThe second half of the two-synonym pair.
contextIf there are more than two words or phrases with the same meaning, such as “macbook, apple mac, mac”, then this field shows the group to which this pair belongs.
similarityA similarity score to measure confidence.
countThe number of different contexts in which this synonym pair appears.
The bigger the number, the higher the quality of the pair.
suggestionThe algorithm automatically selects context, synonym words or phrases, or the synonym_group, and puts it in this field.
Use this field as the field to review.
categoryWhether the synonym is actually a misspelling.

​
Configuration properties

⌘I