{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11481418","patent":{"patent_number":"US-11481418","title":"Natural question generation via reinforcement learning based graph-to-sequence model","assignee":null,"inventors":[],"filing_date":"2020-04-09T00:00:00.000Z","publication_date":"2022-10-25T00:00:00.000Z","cpc_codes":["G06F","G06F","G06F","G06F","G06F","G06F","G06N","G06N","G06N","G06N","G06N","G06N","G06N"],"num_claims":20,"abstract":"For a passage text and a corresponding answer text, perform a word-level soft alignment to obtain contextualized passage embeddings and contextualized answer embeddings, and a hidden level soft alignment on the contextualized passage embeddings and the contextualized answer embeddings to obtain a passage embedding matrix. Construct a passage graph of the passage text based on the passage embedding matrix, and apply a bidirectional gated graph neural network to the passage graph until a final state embedding is determined, during which intermediate node embeddings are fused from both incoming and outgoing edges. Obtain a graph-level embedding from the final state embedding, and decode the final state embedding to generate an output sequence word-by-word. Train a machine learning model to generate at least one question corresponding to the passage text and the answer text, by evaluating the output sequence with a hybrid evaluator combining cross-entropy evaluation and reinforcement learning evaluation."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Natural question generation via reinforcement learning based graph-to-sequence model","description":"For a passage text and a corresponding answer text, perform a word-level soft alignment to obtain contextualized passage embeddings and contextualized answer embeddings, and a hidden level soft alignm","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11481418","license":"CC-BY-4.0-like","license_terms":"AI-generated analysis on this page (summary, layman_explanation, technical_analysis, business_analysis, faqs) may be reused with attribution and a visible link back to the canonical URL above. Patent abstracts, claims, and bibliographic data are USPTO public domain.","required_link":"https://patentable.app/patents/US-11481418","citation_suggestion":"Patentable. \"Natural question generation via reinforcement learning based graph-to-sequence model\" (US-11481418). https://patentable.app/patents/US-11481418","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11481418","json":"https://patentable.app/api/llm-context/US-11481418","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T05:55:54.238Z"}