Structured document generation using document-scale embeddings

A method, the method comprising:

• generating document embeddings within an embedding space based on a set of structured documents by, for a first document of the set of structured documents:
• determining (i) a first vector based on a first segment of the first document and (ii) a second vector based on a second segment of the first document;
• updating a set of association vectors indicating the second segment based on a first distance between the first vector and the second vector;
• and
• generating a first document embedding of the document embeddings in the embedding space based on the set of association vectors;
• generating a candidate vector based on a candidate document;
• determining a result indicating that a second distance between the candidate vector and the first document embedding satisfies a document embedding distance threshold, wherein the first document embedding is associated with the first document;
• and
• in response to the result, generating a new document by providing, to a text generation model, a portion of the candidate document and a portion of the second segment of the first document.

One or more non-transitory, machine-readable media storing program instructions that, when executed by one or more processors, perform operations comprising:

• generating a set of document embeddings within an embedding space based on a set of structured documents by, for a first document of the set of structured documents:
• determining (i) a first vector based on a first segment of the first document and (ii) a second vector based on a second segment of the first document;
• updating a set of association vectors indicating the second segment based on a first distance between the first vector and the second vector;
• and
• generating a first document embedding of the set of document embeddings in the embedding space based on the set of association vectors, wherein the first document embedding is associated with the first document;
• generating a candidate vector based on a candidate document;
• determining a result indicating that a second distance between the candidate vector and the first document embedding of the set of document embeddings satisfies a document embedding distance threshold;
• and
• based on the result, generating a new document by providing, to a text generation model, a portion of the candidate document and a portion of the second segment of the first document.