Abstract: Techniques for improving machine learning and text classification are described. The described techniques include improved processes for collecting training data to train a machine classifier. Some data sets are very large but contain only a small number of positive or negative training examples. The described text classification system obtains training examples by intelligently identifying documents that are likely to present or identify positive or negative training examples. The text classification system employs these techniques to train a classifier to categorize patent claims according some legal rule, such as subject-matter eligibility requirements under patent law.

Abstract: Techniques for improving machine learning and text classification are described. The described techniques include improved processes for collecting training data to train a machine classifier. Some data sets are very large but contain only a small number of positive or negative training examples. The described text classification system obtains training examples by intelligently identifying documents that are likely to present or identify positive or negative training examples. The text classification system employs these techniques to train a classifier to categorize patent claims according some legal rule, such as subject-matter eligibility under 35 U.S.C. 101.

Abstract: Techniques for computer-assisted patent application preparation are described. Some embodiments provide a Patent Application Preparation System (“PAPS”) that facilitates the automatic generation of patent applications (or portions thereof) based on logical claim definitions. The PAPS may receive one or more claim definitions that each define a single patent claim. From these claim definitions, the PAPS may generate claims, figures, written description corresponding to the figures, summary sections, and the like. When a drafter modifies a claim definition, the application portions may be automatically regenerated, so that any changes (e.g., to claim position or terminology) are reflected in the resulting patent application.

Abstract: A method comprising: providing a navigation tree comprising a semantic, hierarchical structure, having one or more paths associated with content of a conventional markup language document and a grammar comprising vocabulary including one or more keywords; receiving a request to access the content; responsive to the request, traversing a path in the navigation tree, if the request includes at least one keyword of the vocabulary, is provided.