Inventor · Arlington, VA, US

Christopher Phipps

16Patents
2h-index
13Co-inventors
40Inventor score

Filing activity: May 12, 2016 → Dec 4, 2019

Most-cited inventions

PatentTitleAreaCited byStatus
US10133724B2 Syntactic classification of natural language sentences with respect to a targeted element Physics 4 Active
US10394950B2 Generation of a grammatically diverse test set for deep question answering systems Physics 2 Active
US10073833B1 Domain-specific method for distinguishing type-denoting domain terms from entity-denoting domain terms Physics 2 Active
US9842096B2 Pre-processing for identifying nonsense passages in documents being ingested into a corpus of a natural language processing system Physics 2 Active
US11093774B2 Optical character recognition error correction model Physics 1 Active
US10558689B2 Leveraging contextual information in topic coherent question sequences Physics 1 Active
US10282066B2 Dynamic threshold filtering for watched questions Physics 0 Active
US10872205B2 Process for identifying completion of domain adaptation dictionary activities Physics 0 Active
US10303763B2 Process for identifying completion of domain adaptation dictionary activities Physics 0 Active
US10565503B2 Dynamic threshold filtering for watched questions Physics 0 Active
US10970533B2 Methods and systems for finding elements in optical character recognition documents Physics 0 Active
US11361229B2 Post-processor for factoid answer conversions into structured relations in a knowledge base Physics 0 Active
US10169328B2 Post-processing for identifying nonsense passages in a question answering system Physics 0 Active
US10073831B1 Domain-specific method for distinguishing type-denoting domain terms from entity-denoting domain terms Physics 0 Active
US11216739B2 System and method for automated analysis of ground truth using confidence model to prioritize correction options Physics 0 Active
US10585898B2 Identifying nonsense passages in a question answering system based on domain specific policy Physics 0 Active

Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.