Entity based search retrieval and ranking
In an example embodiment, one or more query terms are obtained. Then, for each of the one or more query terms, a standardized entity taxonomy is searched to locate a standardized entity that most closely matches the query term, with the standardized entity taxonomy comprising an entity identification for each of a plurality of different standardized entities. A confidence score is then calculated for the query term-standardized entity pair for the standardized entity that most closely matches the query term, and the query term is tagged with the entity identification corresponding to the standardized entity that most closely matches the query term and the calculated confidence score.
1. A computer-implemented method, comprising:
identifying one or more query terms;
for each of the one or more query terms:
searching a standardized entity taxonomy to locate a standardized entity that most closely matches the query term, the standardized entity taxonomy comprising an entity identification for each of a plurality of different standardized entities;
calculating a confidence score for a query term-standardized entity pair comprising the query term and the standardized entity that most closely matches the query term; and
tagging the query term with the entity identification corresponding to the standardized entity that most closely matches the query term based on the calculated confidence score; and
causing a search request having the one or more query terms and the entity identifications tagged to the one or more query terms to be processed.
2. The method of claim 1 , wherein the method further comprises, for each of the one or more query terms, augmenting the search request with a standardized entity and corresponding entity identification for a standardized entity indicated as a synonym for the query term.
3. The method of claim 1 , wherein the method further comprises:
eliminating any standardized entity from the search query that has a corresponding confidence score that does not transgress a preset threshold.
4. The method of claim 1 , wherein the confidence score indicates a statistical likelihood that a user specifying the query term in a search query would have, under ideal circumstances, also entered the corresponding standardized entity in the search query.
5. The method of claim 4 , wherein the confidence score is calculated by using a confidence score model trained via a machine learning algorithm based on member profiles and member activities in a social networking service.
6. The method of claim 4 , wherein the confidence score model is trained based on a statistical analysis of how often users who specify the query term in a search query click on a subsequent result containing the corresponding standardized entity.
7. The method of claim 4 , wherein the confidence score model is trained based on a statistical analysis of how often member profiles listing the query term also list the standardized entity.
8. A system comprising:
a non-transitory computer-readable medium having instructions stored thereon, which, when executed by a processor, cause the system to perform operations comprising:
identifying one or more query terms;
for each of the one or more query terms:
searching a standardized entity taxonomy to locate a standardized entity that most closely matches the query term, the standardized entity taxonomy comprising an entity identification for each of a plurality of different standardized entities;
calculating a confidence score for a query term-standardized entity pair comprising the query term and the standardized entity that most closely matches the query term; and
tagging the query term with the entity identification corresponding to the standardized entity that most closely matches the query term based on the calculated confidence score; and
causing a search request having the one or more query terms and the entity identifications tagged to the one or more query terms to be processed.
9. The system of claim 8 , wherein the operations further comprise, for each of the one or more query terms, augmenting the search request with a standardized entity and corresponding entity identification for a standardized entity indicated as a synonym for the query term.
10. The system of claim 8 , wherein the operations further comprise:
eliminating any standardized entity from the search query that has a corresponding confidence score that does not transgress a preset threshold.
11. The system of claim 8 , wherein the confidence score indicates a statistical likelihood that a user specifying the query term in a search query would have, under ideal circumstances; also entered the corresponding standardized entity in the search query.
12. The system of claim 11 , wherein the confidence score is calculated by using a confidence score model trained via a machine learning algorithm based on member profiles and member activities in a social networking service.
13. The system of claim 11 , wherein the confidence score model is trained based on a statistical analysis of how often users who specify the query term in a search query click on a subsequent result containing the corresponding standardized entity.
14. The system of claim 11 , wherein the confidence score model is trained based on a statistical analysis of how often member profiles listing the query term also list the standardized entity.
15. A non-transitory machine-readable storage medium comprising instructions, which when implemented by one or more machines, cause the one or more machines to perform operations comprising:
identifying one or more query terms;
for each of the one or more query terms:
searching a standardized entity taxonomy to locate a standardized entity that most closely matches the query term, the standardized entity taxonomy comprising an entity identification for each of a plurality of different standardized entities;
calculating a confidence score for a query term-standardized entity pair comprising the query term and the standardized entity that most closely matches the query term; and
tagging the query term with the entity identification corresponding to the standardized entity that most closely matches the query term based on the calculated confidence score; and
causing a search request having the one or more query terms and the entity identifications tagged to the one or more query terms to be processed.
16. The non-transitory machine-readable storage medium of claim 15 , wherein the method further comprises, for each of the one or more query terms, augmenting the search request with a standardized entity and corresponding entity identification for a standardized entity indicated as a synonym for the query term.
17. The non-transitory machine-readable storage medium of claim 15 , wherein the method further comprises:
eliminating any standardized entity from the search query that as a corresponding confidence score that does not transgress a preset threshold.
18. The non-transitory machine-readable storage medium of claim 15 , wherein the confidence score indicates a statistical likelihood that a user specifying the query term in a search query would have, under ideal circumstances, also entered the corresponding standardized entity in the search query.
19. The non-transitory machine-readable storage medium of claim 18 , wherein the confidence score is calculated by using a confidence score model trained via a machine learning algorithm based on member profiles and member activities in a social networking service.
20. The non-transitory machine-readable storage medium of claim 18 , wherein the confidence score model is trained based on a statistical analysis of how often users who specify the query term in a search query click on a subsequent result containing the corresponding standardized entity.