{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11526676","patent":{"patent_number":"US-11526676","title":"Implicit discourse relation classification with contextualized word representation","assignee":null,"inventors":[],"filing_date":"2020-03-13T00:00:00.000Z","publication_date":"2022-12-13T00:00:00.000Z","cpc_codes":["G06F","G06F","G06F","G06N","G06N","G06N"],"num_claims":21,"abstract":"A method includes: initializing a list of token embeddings, each of the token embeddings corresponding to a tokenized word from text in a corpus of text; generating a graph for a group of consecutive words s from the text, said graph including binary relations between pairs of tokenized words of the group of consecutive words; selecting the token embeddings representing the words of the group of consecutive words from the list of token embeddings; computing a tensor of binary relations as the product between a matrix of the selected token embeddings and a tensor representing discourse relations, the computed tensor representing the binary relations between the pairs of tokenized words; computing a loss using the computed tensor; optimizing the list of token embeddings using the computed loss. The above may be repeated until the computed loss is within a predetermined range."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Implicit discourse relation classification with contextualized word representation","description":"A method includes: initializing a list of token embeddings, each of the token embeddings corresponding to a tokenized word from text in a corpus of text; generating a graph for a group of consecutive ","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11526676","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-11526676","citation_suggestion":"Patentable. \"Implicit discourse relation classification with contextualized word representation\" (US-11526676). https://patentable.app/patents/US-11526676","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11526676","json":"https://patentable.app/api/llm-context/US-11526676","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-30T17:19:52.925Z"}