Machine learning techniques for updating documents generated by a natural language generation (NLG) engine

A system for updating document content, the system comprising:

• at least one computer hardware processor to perform:
• identifying a first text segment in a document to be updated with additional content;
• identifying, using the first text segment, content from at least one data source, the content including a plurality of content segments;
• identifying, using a first machine learning model and from among the plurality of content segments, at least one causal text segment having a causal structure, the at least one causal text segment including a first causal text segment;
• identifying, using a second machine learning model different from the first machine learning model, cause and effect sub-segments of the first causal text segment;
• generating a second text segment for use in updating the document by using the cause sub-segment;
• and
• updating the document using the second text segment.

At least one non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by at least one processor, cause the at least one processor to perform a method for updating document content, the method comprising:

• identifying a first text segment in a document to be updated with additional content;
• identifying, using the first text segment, content from at least one data source, the content including a plurality of content segments;
• identifying, using a first machine learning model and from among the plurality of content segments, at least one causal text segment having a causal structure, the at least one causal text segment including a first causal text segment;
• identifying, using a second machine learning model different from the first machine learning model, cause and effect sub-segments of the first causal text segment;
• generating a second text segment for use in updating the document by using the cause sub-segment;
• and
• updating the document using the second text segment.