Identification of permissions-aware enterprise-specific term substitutions
Methods and apparatuses for providing a real-time enterprise knowledge assistant that automatically responds to user comments and questions via a graphical user interface are described. The enterprise knowledge assistant may display automated responses to questions provided by users within a persistent chat channel (or other communications channel). The information displayed or referenced (e.g., via a linked electronic document) within an automated response to a user's factual question may be determined based on access rights to linked documents and the number of electronic interactions between users, such as the number of times that users co-edited or collaborated on documents (e.g., programming code). Upon detection that at least a portion of a user's message within a chat channel has been classified as a factual question, the enterprise knowledge assistant may access question and answer pairings stored within a frequently asked questions database and display an authorized answer.
1. A method, comprising:
acquiring a first document that includes a first sentence with a first term;
determining a first set of synonym candidates for the first term within the first sentence while the first term is masked;
determining a first set of probabilities for the first set of synonym candidates;
detecting that a second term of the first set of synonym candidates corresponds with at least a threshold probability of being a correct term based on the first set of probabilities;
identifying a second sentence within a second document different from the first document that includes the second term in response to detection that that the second term of the first set of synonym candidates corresponds with at least the threshold probability of being a correct term;
determining a second set of synonym candidates for the second term within the second sentence while the second term is masked;
determining a second set of probabilities for the second set of synonym candidates;
detecting that the first term of the second set of synonym candidates corresponds with at least the threshold probability of being a correct term based on the second set of probabilities;
adding the first term and the second term to a synonyms database in response to detection that the first term of the second set of synonym candidates corresponds with at least the threshold probability of being a correct term and detection that the second term of the first set of synonym candidates corresponds with at least the threshold probability of being a correct term;
acquiring a search query that includes the first term;
adding the second term to the search query in response to detecting that the search query includes the first term;
generating search results for the updated search query; and
displaying the search results for the updated search query.
2. The method of claim 1 , further comprising:
removing the first term from the updated search query prior to generating the search results for the updated search query.
3. The method of claim 1 , further comprising:
detecting that the second term has a higher frequency of usage compared with the first term within a set of documents and removing the first term from the updated search query in response to detection that the second term has the higher frequency of usage compared with the first term within the set of documents.
4. The method of claim 1 , further comprising:
detecting that the second term includes a greater number of characters than the first term and removing the first term from the updated search query in response to detection that the second term includes a greater number of characters than the first term.
5. The method of claim 1 , wherein:
the displaying the search results includes displaying the search results using a display of a mobile computing device.
6. A method, comprising:
acquiring a set of documents that includes a first term and a second term;
determining a first set of synonym candidates for the first term while the first term is masked;
determining a first set of probabilities for the first set of synonym candidates;
detecting that a second term of the first set of synonym candidates corresponds with at least a threshold probability of being a correct term based on the first set of probabilities;
determining a second set of synonym candidates for the second term while the second term is masked;
determining a second set of probabilities for the second set of synonym candidates;
detecting that the first term of the second set of synonym candidates corresponds with at least the threshold probability of being a correct term based on the second set of probabilities;
adding the first term and the second term to a synonyms database;
acquiring a search query that includes the first term;
generating an updated search query in response to detecting that the search query includes the first term, the generating the updated search query includes adding the second term to the search query;
generating search results for the updated search query; and
displaying the search results for the updated search query.
7. The method of claim 6 , wherein:
the updated search query includes the first term and the second.
8. The method of claim 6 , further comprising:
detecting that the second term has a higher frequency of usage compared with the first term within the set of documents and removing the first term from the updated search query in response to detection that the second term has the higher frequency of usage compared with the first term within the set of documents.
9. The method of claim 6 , further comprising:
detecting that the second term includes a greater number of characters than the first term and removing the first term from the updated search query in response to detection that the second term includes a greater number of characters than the first term.
10. The method of claim 6 , wherein:
the displaying the search results includes displaying the search results using a display of a mobile computing device.
11. The method of claim 6 , wherein:
the set of documents comprises documents associated with a people cluster.
12. The method of claim 6 , wherein:
the first term and the second term do not share a common root word.
13. The method of claim 6 , wherein:
the set of documents includes a first document that includes the first term and a second document that includes the second term.
14. The method of claim 13 , wherein:
the first document includes a first sentence with the first term; and
the second document includes a second sentence with the second term.
15. A search system, comprising:
a storage device configured to store a synonyms database; and
one or more processors in communication with the storage device configured to:
acquire a set of documents that includes a first term and a second term;
determine a first set of synonym candidates for the first term while the first term is masked;
determine a first set of probabilities for the first set of synonym candidates;
detect that a second term of the first set of synonym candidates corresponds with at least a threshold probability of being a correct term based on the first set of probabilities;
determine a second set of synonym candidates for the second term while the second term is masked;
determine a second set of probabilities for the second set of synonym candidates;
detect that the first term of the second set of synonym candidates corresponds with at least the threshold probability of being a correct term based on the second set of probabilities;
add the first term and the second term to the synonyms database;
acquire a search query that includes the first term;
generate an updated search query in response to detection that the search query includes the first term, the generation of the updated search query includes adding the second term to the search query;
generate search results for the updated search query; and
cause the search results for the updated search query to be displayed.
16. The search system of claim 15 , wherein:
the one or more processors are configured to detect that the second term has a higher frequency of usage compared with the first term within the set of documents and remove the first term from the updated search query in response to detection that the second term has the higher frequency of usage compared with the first term within the set of documents.
17. The search system of claim 15 , wherein:
the one or more processors are configured to detect that the second term includes a greater number of characters than the first term and remove the first term from the updated search query in response to detection that the second term includes a greater number of characters than the first term.
18. The search system of claim 15 , wherein:
the first term and the second term do not share a common root word.
19. The search system of claim 15 , wherein:
the set of documents includes a first document that includes the first term and a second document that includes the second term.
20. The search system of claim 15 , wherein:
the one or more processors are configured to cause the search results to be displayed using a display of a mobile computing device; and
the updated search query includes the first term and the second term.