receiving input data;

extracting a plurality of topic entities from the input data;

grouping one or more topic entities of the plurality of topic entities into one or more topic clusters;

identifying one or more linguistic modalities associated in the input data with one or more of the plurality of topic entities;

for a first topic cluster of the one or more topic clusters, constructing a data structure comprising a plurality of nodes, wherein each node of the data structure respectively represents a topic entity extracted from the input data and grouped into the first topic cluster, and wherein a first node of the data structure is associated with a second node of the data structure based on the first node and the second node respectively representing a first topic entity and a second topic entity associated in the input data with a common one of the one or more identified linguistic modalities;

construct a plurality of data structures, each data structure comprising a plurality of nodes included in a respective topic cluster of the one or more topic clusters, wherein each of the nodes of each respective data structure represents a respective topic entity grouped into the respective topic cluster, and wherein nodes within each of the plurality of data structures are interconnected based on the respective topic entities represented by the nodes being associated in the input data with common identified linguistic modalities;

automatically generating a response to an input query using a selected data structure of the plurality of data structures, wherein automatically generating a response to the input query comprises: