Natural language generation using knowledge graph incorporating textual summaries

A non-transitory computer readable medium including instructions that, when executed by one or more processors, cause the one or more processors to perform a set of actions for producing a textual output in response to a textual input relating to a domain, the set of actions including:

• receiving a natural-language textual sequence representing the textual input from a user;
• retrieving, from a knowledge graph associated with the domain:
• a first textual passage based on a first ranking with respect to the natural-language textual sequence,
• a first textual summary summarizing textual information in a first vicinity of the first textual passage,
• a second textual passage based on a second ranking with respect to a comparison of the second textual passage and the natural-language textual sequence,
• a second textual summary summarizing textual information in a second vicinity of the second textual passage, and
• a third textual summary based on a third ranking with respect to the natural-language textual sequence, wherein:
• the knowledge graph includes a tree structure in which leaves correspond to textual passages and nodes correspond to textual summaries at multiple levels of summarization the knowledge graph is generated based on the textual passages, descriptions of associations between the textual passages, and textual summaries obtained by providing at least a portion of a corpus of textual information to a language model, the corpus of textual information includes a plurality of documents, and
• the language model is provided with previously generated textual summaries at a higher level or a lower level to reduce duplication of information included in the textual summaries between a plurality of levels, wherein the higher level corresponds to the second textual summary, and the lower level corresponds to the first textual summary, where the second vicinity includes more text than the first vicinity and includes the text of the first vicinity;
• retrieving the first textual summary by traversing from a leaf corresponding to the first textual passage to a connected node in the tree structure;
• tracking previously retrieved textual summaries and suppressing retrieval of previously retrieved textual summaries;
• obtaining the textual output in response to the textual input from the language model by providing input to the language model based on the natural-language textual sequence, the first textual passage, the first textual summary, the second textual passage, the second textual summary, and the third textual summary;
• and
• providing the output based on the textual output.

A system including at least one processor and at least one computer readable medium including instructions that, when executed by the at least one processor, cause the at least one processor to perform a set of actions for producing a textual output in response to a textual input relating to a domain, the set of actions including:

• receiving a natural-language textual sequence representing the textual input from a user;
• retrieving, from a knowledge graph associated with the domain:
• a first textual passage based on a first ranking with respect to the natural-language textual sequence,
• a first textual summary summarizing textual information in a first vicinity of the first textual passage,
• a second textual passage based on a second ranking with respect to a comparison of the second textual passage and the natural-language textual sequence,
• a second textual summary summarizing textual information in a second vicinity of the second textual passage, and
• a third textual summary based on a third ranking with respect to the natural-language textual sequence, wherein:
• the knowledge graph includes a tree structure in which leaves correspond to textual passages and nodes correspond to textual summaries at multiple levels of summarization the knowledge graph is generated based on the textual passages, descriptions of associations between the textual passages, and textual summaries obtained by providing at least a portion of a corpus of textual information to a language model, the corpus of textual information includes a plurality of documents, and
• the language model is provided with previously generated textual summaries at a higher level or a lower level to reduce duplication of information included in the textual summaries between a plurality of levels, wherein the higher level corresponds to the second textual summary, and the lower level corresponds to the first textual summary, where the second vicinity includes more text than the first vicinity and includes the text of the first vicinity;
• retrieving the first textual summary by traversing from a leaf corresponding to the first textual passage to a connected node in the tree structure;
• tracking previously retrieved textual summaries and suppressing retrieval of previously retrieved textual summaries;
• obtaining the textual output in response to the textual input from the language model by providing input to the language model based on the natural-language textual sequence, the first textual passage, the first textual summary, the second textual passage, the second textual summary, and the third textual summary;
• and
• providing the output based on the textual output.