~ Semantic Search Art ~

This is partial list of US patents for Natural Language Processing and Semantic Search. I selected for this list those that I found interesting and educating. Most US patents in this area belong to the following classes and subclasses
  • 704 (1, 4, 9, 10, 240, 257, 270)
  • 706 (12, 14, 20, 47, 55)
  • 707 (3, 602, 603, 705, 706, 707, 708, 709, 713, 726, 736, 737, 739, 740, 752, 755, 758)
  • 715 (254, 255, 256, 259)
For those who examined RESEARCH section of this site and understand basic concepts explained in it, the patented subject matter should be clear.

  • US Patent 8,429,163. Content similarity pyramid.
  • US Patent 8,417,653. Automated classification algorithm comprising at least one input-invariant part.
  • US Patent 8,402,369. Multiple-document summarization using document clustering.
  • US Patent 8,402,029. Clustering system and method.
  • US Patent 8,401,841. Retrieval of Documents Using Language Models.
  • US Patent 8,396,871. Document classification and characterization.
  • US Patent 8,364,467. Content-based classification.
  • US Patent 8,306,818. Discriminative training of language models for text and speech classification.
  • US Patent 8,271,453. Paraphrase acquisition.
  • US Patent 8,250,008. Decision tree refinement.
  • US Patent 8,170,867. System for extracting information from a natural language text.
  • US Patent 8,046,348. Method and apparatus for concept-based searching of natural language discourse.
  • US Patent 8,041,697. Semi-automatic example-based induction of semantic translation rules to support natural language search.
  • US Patent 8,037,043. Information retrieval system.
  • US Patent 8,032,827. Automatic generation of document summaries through use of structured text.
  • US Patent 8,027,979. Document summarization.
  • US Patent 8,019,760. Clustering system and method.
  • US Patent 8,005,815. Search engine.
  • US Patent 8,005,665. Method and apparatus for generating a language independent document abstract.
  • US Patent 7,996,210. Large-scale sentiment analysis.
  • US Patent 7,987,176. Mixed initiative semantic search.
  • US Patent 7,984,035. Context-based document search.
  • US Patent 7,983,901. Computer-aided natural language annotation.
  • US Patent 7,971,150. Document categorisation system.
  • US Patent 7,966,174. Automatic clustering of tokens from a corpus for grammar acquisition.
  • US Patent 7,962,329. Text-to-scene conversion.
  • US Patent 7,962,326. Semantic answering system and method.
  • US Patent 7,957,971. System and method of spoken language understanding using word confusion networks.
  • US Patent 7,950,062. Fingerprinting based entity extraction.
  • US Patent 7,945,527. Methods and systems for interpreting text using intelligent glossaries.
  • US Patent 7,933,859. Systems and methods for predictive coding.
  • US Patent 7,925,496. Method for summarizing natural language text.
  • US Patent 7,912,868. Advertisement placement method and system using semantic analysis.
  • US Patent 7,865,592. Using semantic networks to develop a social network.
  • US Patent 7,844,566. Latent semantic clustering.
  • US Patent 7,844,449. Scalable probabilistic latent semantic analysis.
  • US Patent 7,809,726. Mechanism for unsupervised clustering.
  • US Patent 7,809,704. Combining spectral and probabilistic clustering.
  • US Patent 7,747,625. Organizing a collection of objects.
  • US Patent 7,716,163. Method and system for defining semantic categories and actions.
  • US Patent 7,676,463. Information exploration systems and method.
  • US Patent 7,529,765. Methods, apparatus, and program products for performing incremental probabilistic latent semantic analysis.
  • US Patent 7,512,605. Document clustering based on cohesive terms.
  • UP Patent 7,483,892. Method and system for optimally searching a document database using a representative semantic space.
  • US Patent 7,406,456. Construction of trainable semantic vectors and clustering, classification, and searching using trainable semantic vectors.
  • US Patent 7,403,890. Multi-dimensional method and apparatus for automated language interpretation.
  • US Patent 7,349,917. Hierarchical categorization method and system with automatic local selection of classifiers.
  • US Patent 7,325,006. System and method for category organization.
  • US Patent 7,139,695. Method for categorizing documents by multilevel feature selection and hierarchical clustering based on parts of speech tagging.
  • US Patent 6,442,555. Automatic categorization of documents using document signatures.
  • US Patent 6,304,864. System for retrieving multimedia information from the internet using multiple evolving intelligent agents.
  • US Patent 6,349,296. Method for clustering closely resembling data objects.
  • US Patent 6,269,368. Information retrieval using dynamic evidence combination.
  • US Patent 6,263,335. Information extraction system and method using concept-relation-concept (CRC) triples.
  • US Patent 6,189,002. Process and system for retrieval of documents using context-relevant semantic profiles.
  • US Patent 6,026,388. User interface and other enhancements for natural language information retrieval system and method.
  • US Patent 4,839,853. Computer Information Retrieval Using Latent Semantic Structure.