Feedback techniques for processing natural language queries

A system comprising:

• a processor;
• a memory;
• a synonym reconciliation module to:
• render a visual indicator and a customization tag associated with the visual indicator on a user interface in response to a user request received from a user of an organization;
• display, on the user interface, one or more data fields associated with the visual indicator in response to detecting a user selection of the customization tag, wherein each of the one or more data fields is to represent a subset, from one or more subsets, of data stored within a dataset associated with the user, wherein the data is graphically representable through the visual indicator;
• receive, from the user, a first input comprising one or more additional synonyms to be assigned to at least one data field from the one or more data fields;
• retrieve the one or more additional synonyms from a first database, wherein the first database stores user-provided synonyms;
• obtain a list of pre-assigned synonyms associated with the at least one data field from a second database for processing of natural language queries in relation to one or more topics, wherein the user is authorized to raise a natural language query in relation to the one or more topics, and wherein the natural language query is to be processed using at least in part the at least one data field;
• reconcile the one or more additional synonyms with the list of pre-assigned synonyms to obtain an updated list of pre-assigned synonyms for the at least one data field;
• and
• store the updated list of pre-assigned synonyms in the second database in association with the at least one data field, wherein the updated list of pre-assigned synonyms in the second database is to be used for future processing of natural language queries raised for the one or more topics;
• and
• a query processing module to:
• process a natural language query for the one or more topics using the updated list of pre-assigned synonyms.

A non-transitory computer-readable medium comprising instructions for executing feedback techniques for processing of natural language queries, the instructions being executable by a processing resource to:

• receive a customization request in relation to a visual indicator allocated to a user of an organization;
• display, on a user interface, one or more data fields associated with the visual indicator, wherein each of the one or more data fields is to represent a subset, from one or more subsets, of the data stored within one or more datasets associated with the user, wherein the data is graphically representable through the visual indicator;
• receive, from the user, a first input comprising one or more additional synonyms to be assigned to at least one data field from the one or more data fields;
• retrieve the one or more additional synonyms from a first database, wherein the first database stores user-provided synonyms;
• obtain a list of pre-assigned synonyms associated with the at least one data field from a second database for processing of natural language queries in relation to one or more topics, wherein the user is authorized to raise a natural language query in relation to the one or more topics, and wherein the natural language query is to be processed using at least in part the at least one data field;
• compare the one or more additional synonyms with the list of pre-assigned synonyms to determine at least one distinct synonym;
• incorporate the at least one distinct synonym in the list of pre-assigned synonyms to obtain an updated list of pre-assigned synonyms for the at least one data field, wherein the updated list of pre-assigned synonyms is to be used for future processing of natural language queries raised for the one or more topics;
• and
• store the updated list of pre-assigned synonyms in the second database in association with the at least one data field, wherein the updated list of pre-assigned synonyms in the second database is to be used for future processing of natural language queries raised for the one or more topics.