System and method for generating abstractive summary

A summary generation unit, for generating abstractive summary, the summary generation unit comprises:

• a processor;
• and
• a memory communicatively coupled to the processor, wherein the memory stores processor executable instructions, which, on execution, cause the processor to:
• receive a query for generating the abstractive summary from a document among a plurality of documents stored in a document database and splitting the query into one or more lexical units;
• generate a semantic graph and a graph index based on a role assigned to the one or more lexical units in the query;
• determine a measure of information of retrieved one or more sentences from the document, wherein the one or more sentences having a semantic graph analogous to the generated semantic graph of the query are retrieved from the document, wherein the measure of information comprises at least one of a semantic relationship between one or more lexical units of the retrieved one or more sentences with the one or more lexical units of the query and a correlation score of the retrieved one or more sentences with the query;
• and
• perform re-ordering and re-phrasing of at least one of the retrieved one or more sentences based on the computed measure of information and the one or more lexical units in the retrieved one or more sentences to generate the abstractive summary, wherein the retrieved one or more sentences are grouped using an Artificial Intelligence based clustering algorithm, and wherein re-phrasing the retrieved one or more sentences comprises identifying sequence of semantic slots in the retrieved one or more sentences, and analyzing inter dependency among the semantic slots and choosing a lexical unit based on at least one of similarity score and word embedding for rephrasing the one or more lexical units in the retrieved one or more sentences.

A non-transitory computer readable medium including instructions stored thereon for generating abstractive summary, that when processed by at least one processor cause a device to perform operations comprising:

• receiving a query for generating an abstractive summary from a document among a plurality of documents stored in a document database and splitting the query into one or more lexical units;
• generating a semantic graph and a graph index based on a role assigned to the one or more lexical units in the query;
• determining a measure of information of retrieved one or more sentences from the document, wherein the one or more sentences having a semantic graph analogous to the generated semantic graph of the query are retrieved from the document, wherein the measure of information comprises at least one of a semantic relationship between one or more lexical units of the retrieved one or more sentences with the one or more lexical units of the query and a correlation score of the retrieved one or more sentences with the query;
• and
• performing re-ordering and re-phrasing of at least one of the retrieved one or more sentences based on the determined measure of information and the one or more lexical units in the retrieved one or more sentences to generate the abstractive summary, wherein the retrieved one or more sentences are grouped using an Artificial Intelligence based clustering algorithm, and wherein re-phrasing the retrieved one or more sentences comprises identifying sequence of semantic slots in the retrieved one or more sentences, and analyzing inter dependency among the semantic slots and choosing a lexical unit based on at least one of similarity score and word embedding for rephrasing the one or more lexical units in the retrieved one or more sentences.