US Patent No: 5,111,398

Number of patents in Portfolio can not be more than 2000

Processing natural language text using autonomous punctuational structure

Stats

ATTORNEY / AGENT: (SPONSORED)
 

Importance

Loading Importance Indicators... loading....

Abstract

A technique for processing natural language text uses a data structure that includes structure data in the text data. The structure data indicates an autonomous punctuational structure of the text, a punctuational structure that is independent of the lexical content of the text and therefore can be manipulated without considering the meaning of the words in the text. The data structure can be a tree in which each node has a textual type such as a paragraph, sentence, clause, phrase, or word. The data structure could alternatively be parallel data sequences, one with codes indicating the text's characters and the other with codes indicating textual types. The data structure is produced and maintained using a grammar of textual types, indicating for each textual type the textual types of units into which it can properly be divided. During editing, a text sequence is generated by applying rendering rules to the data structure, and the text is presented to the user based on the text sequence. Prior to generating the text sequence, information relating to punctuational features is propagated through the data structure. User signals requesting editing operations are applied to modify the data structure using operations rules, and the user's pointing or selecting signals are mapped onto the data structure. The modified data structure is checked with the grammar of textual types to ensure that it has an autonomous punctuational structure. A modified text sequence is then generated, and a modified text is displayed based on it.

Loading the Abstract Image... loading....

First Claim

Related Publications

Loading Related Publications... loading....

Patent Owner(s)

Patent OwnerAddressTotal Patents
XEROX CORPORATIONSTAMFORD, CT17094

International Classification(s)

  • [Classification Symbol]
  • [Patents Count]

Inventor(s)

Inventor Name Address # of filed Patents Total Citations
Abbott, Curtis Menlo Park, CA 10 351
Nunberg, Geoffrey D San Francisco, CA 6 125
Smith, Brian C Fort Worth, TX 25 283
Stansbury, H Tayloe Mountain View, CA 1 87

Cited Art

Patent Info (Count) # Cites Year
 
HITACHI, LTD. (2)
4,641,264 Method for automatic translation between natural languages 68 1982
4,958,285 Natural language processing system 14 1988
 
SHARP KABUSHIKI KAISHA (2)
4,594,686 Language interpreter for inflecting words from their uninflected forms 31 1983
4,964,030 Apparatus for translating sentences containing punctuation marks 16 1987
 
BURROUGHS SYSTEM DEVELOPMENT CORPORATION, A CORP. OF DE. (1)
4,597,057 System for compressed storage of 8-bit ASCII bytes using coded strings of 4 bit nibbles 48 1981
 
INTERNATIONAL BUSINESS MACHINES CORPORATION (1)
4,674,065 System for detecting and correcting contextual errors in a text processing system 111 1985
 
KABUSHIKI KAISHA TOSHIBA (1)
4,821,230 Machine translation system 29 1987
 
KOKUSAI DENSHIN DENWA KABUSHIKI KAISHA (1)
4,599,691 Tree transformation system in machine translation system 43 1983
 
TOKYO SHIBAURA DENKI KABUSHIKI KAISHA (1)
4,586,160 Method and apparatus for analyzing the syntactic structure of a sentence 45 1983
 
VANTAGE TECHNOLOGY HOLDINGS, LLC (1)
4,773,009 Method and apparatus for text analysis 63 1986

Patent Citation Ranking

Forward Cites

Patent Info (Count) # Cites Year
 
INTERNATIONAL BUSINESS MACHINES CORPORATION (14)
7,127,450 Intelligent discard in information access system 4 2000
6,745,181 Information access method 23 2000
6,711,561 Prose feedback in information access system 18 2000
7,136,846 Wireless information retrieval 8 2001
7,343,372 Direct navigation for information retrieval 1 2002
8,290,768 System and method for determining a set of attributes based on content of communications 0 2002
7,243,095 Prose feedback in information access system 8 2003
7,376,641 Information retrieval from a collection of data 7 2004
7,644,057 System and method for electronic communication management 4 2004
7,756,810 Software tool for training and testing a knowledge base 1 2007
7,752,159 System and method for classifying text 4 2007
7,788,082 Computational linguistic statements for providing an autonomic computing environment 0 2007
7,783,643 Direct navigation for information retrieval 0 2008
7,702,677 Information retrieval from a collection of data 6 2008
 
SONY ELECTRONICS INC. (11)
6,442,524 Analyzing inflectional morphology in a spoken language translation system 26 1999
6,356,865 Method and apparatus for performing spoken language translation 38 1999
6,282,507 Method and apparatus for interactive source language expression recognition and alternative hypothesis presentation and selection 40 1999
6,278,968 Method and apparatus for adaptive speech recognition hypothesis construction and selection in a spoken language translation system 99 1999
6,266,642 Method and portable apparatus for performing spoken language translation 46 1999
6,243,669 Method and apparatus for providing syntactic analysis and data structure for translation knowledge in example-based language translation 48 1999
6,223,150 Method and apparatus for parsing in a spoken language translation system 45 1999
6,374,224 Method and apparatus for style control in natural language generation 22 1999
6,928,448 System and method to match linguistic structures using thesaurus information 10 1999
6,778,949 Method and system to analyze, transfer and generate language expressions using compiled instructions to manipulate linguistic structures 30 1999
6,535,886 Method to compress linguistic structures 18 1999
 
SYNCHRONOSS TECHNOLOGIES, INC. (10)
8,156,074 Data transfer and synchronization system 0 2000
8,073,954 Method and apparatus for a secure remote access system 0 2000
7,895,334 Remote access communication architecture apparatus and method 7 2000
7,293,074 Performing server actions using template with field that can be completed without obtaining information from a user 23 2000
6,934,767 Automatically expanding abbreviated character substrings 27 2000
7,634,509 Personal information space management system and method 1 2003
8,315,976 Data transfer and synchronization system 0 2008
8,442,943 Data transfer and synchronization between mobile systems using change log 0 2008
8,181,111 System and method for providing social context to digital activity 3 2008
8,255,006 Event dependent notification system and method 1 2009
 
MICROSOFT CORPORATION (7)
5,966,686 Method and system for computing semantic logical forms from syntax trees 86 1996
7,526,424 Sentence realization model for a natural language generation system 0 2002
7,539,940 System and method for converting between text formatting or markup language formatting and outline structure 0 2002
6,829,602 System and method for using a compressed trie to estimate like predicates 4 2002
7,861,269 EPG data 1 2003
7,519,611 System and method for using a compressed trie to estimate like predicates 0 2004
8,010,980 EPG data 0 2010
 
QPS TECH. LIMITED LIABILITY COMPANY (5)
7,711,672 Semantic network methods to disambiguate natural language meaning 14 2002
8,396,824 Automatic data categorization with optimally spaced semantic seed terms 0 2007
8,204,844 Systems and methods to increase efficiency in semantic networks to disambiguate natural language meaning 0 2009
8,135,660 Semantic network methods to disambiguate natural language meaning 0 2009
8,200,608 Semantic network methods to disambiguate natural language meaning 0 2010
 
XEROX CORPORATION (4)
6,973,423 Article and method of automatically determining text genre using surface features of untagged texts 4 1998
6,505,150 Article and method of automatically filtering information retrieval results using test genre 8 1998
6,321,372 Executable for requesting a linguistic service 25 1998
8,280,718 Method to preserve the place of parentheses and tags in statistical machine translation systems 0 2009
 
AT&T INTELLECTUAL PROPERTY II, L.P. (3)
7,734,958 Method and apparatus for a programming language having fully undoable, timed reactive instructions 2 2003
7,966,605 Method and apparatus for a programming language having fully undoable, timed reactive instructions 2 2006
8,112,671 Method and apparatus for a programming language having fully undoable, timed reactive instructions 3 2007
 
XI TECHNOLOGIES, INC. (3)
7,496,559 Apparatus and methods for locating data 6 2003
7,424,510 Methods and systems for Web-based incremental searches 18 2003
7,370,035 Methods and systems for search indexing 13 2003
 
AT&T CORP. (2)
7,203,866 Method and apparatus for a programming language having fully undoable, timed reactive instructions 7 2002
7,174,481 Method and apparatus for a programming language having fully undoable, timed reactive instructions 3 2003
 
FUTURE SEARCH HOLDINGS, INC. (2)
7,945,914 Methods and systems for performing operations in response to detecting a computer idle condition 1 2004
8,019,741 Apparatus and methods for locating data 0 2009
 
GOOGLE INC. (2)
8,010,344 Dictionary word and phrase determination 3 2007
8,412,517 Dictionary word and phrase determination 0 2011
 
ADOBE SYSTEMS INCORPORATED (1)
8,397,157 Context-free grammar 0 2006
 
AYECON REMOTE LLC (1)
6,411,973 Method for facilitating user access to stored information in an electronic text 14 1996
 
BINARY SERVICES LIMITED LIABILITY COMPANY (1)
5,475,588 System for decreasing the time required to parse a sentence 53 1993
 
CANON KABUSHIKI KAISHA (1)
5,870,701 Control signal processing method and apparatus having natural language interfacing capabilities 14 1997
 
CANON RESEARCH CENTRE EUROPE LTD. (1)
6,304,601 Data compression apparatus 8 1998
 
CERNER INNOVATION, INC. (1)
5,715,449 Method for generating structured medical text through user selection of displayed text and rules 40 1994
 
COGNISPHERE, INC. (1)
6,941,513 System and method for text structuring and text generation 9 2001
 
COLLOGUE CORPORATION (1)
5,937,400 Method to quantify abstraction within semantic networks 45 1997
 
EDUCATIONAL TESTING SERVICE, A CORPORATION OF NEW YORK (1)
5,259,766 Method and system for interactive computer science testing, anaylsis and feedback 145 1991
 
FUJITSU LIMITED (1)
5,530,863 Programming language processing system with program translation performed by term rewriting with pattern matching 19 1990
 
FUSIONONE, INC. (1)
7,818,435 Reverse proxy mechanism for retrieving electronic content associated with a local network 1 2000
 
HTC CORPORATION (1)
7,716,195 Search methods 0 2005
 
INTELLISYNC CORPORATION (1)
6,496,835 Methods for mapping data fields from one data set to another in a data processing environment 22 2001
 
KING FAHD UNIVERSITY OF PETROLEUM AND MINERALS (1)
8,219,386 Arabic poetry meter identification system and method 0 2009
 
NCR CORPORATION (1)
5,701,452 Computer generated structure 30 1995
 
POLKWOSKI CAPITAL, L.L.C. (1)
6,279,018 Abbreviating and compacting text to cope with display space constraint in computer software 55 1999
 
POTTER VOICE TECHNOLOGIES LLC (1)
5,729,659 Method and apparatus for controlling a digital computer using oral input 53 1995
 
RICOH COMPANY, LTD. (1)
5,331,554 Method and apparatus for semantic pattern matching for text retrieval 47 1992
 
ROBERT D. LINDNER, JR. (1)
6,865,370 Learning method and system based on questioning 9 2003
 
SDL ENTERPRISE TECHNOLOGIES INC. (1)
6,782,384 Method of and system for splitting and/or merging content to facilitate content processing 2 2001
 
SHARP KABUSHIKI KAISHA (1)
5,587,902 Translating system for processing text with markup signs 69 1993
 
VANTAGE TECHNOLOGY HOLDINGS, LLC (1)
5,890,103 Method and apparatus for improved tokenization of natural language text 70 1996
 
VERITY, INC. (1)
6,629,087 Methods for creating and editing topics for virtual robots conversing in natural language 18 1999
 
Other [Check patent profile for assignment information] (1)
6,684,188 Method for production of medical records and other technical documents 64 1996