Patents by Inventor Kevin Knight

Kevin Knight has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Named entity translation
    Patent number: 7580830
    Abstract: Translating named entities from a source language to a target language. In general, in one implementation, the technique includes: generating potential translations of a named entity from a source language to a target language using a pronunciation-based and spelling-based transliteration model, searching a monolingual resource in the target language for information relating to usage frequency, and providing output including at least one of the potential translations based on the usage frequency information.
    Type: Grant
    Filed: June 7, 2007
    Date of Patent: August 25, 2009
    Assignee: University of Southern California
    Inventors: Yaser Al-Onaizan, Kevin Knight
  • Phrase to phrase joint probability model for statistical machine translation
    Patent number: 7454326
    Abstract: A machine translation (MT) system may utilize a phrase-based joint probability model. The model may be used to generate source and target language sentences simultaneously. In an embodiment, the model may learn phrase-to-phrase alignments from word-to-word alignments generated by a word-to-word statistical MT system. The system may utilize the joint probability model for both source-to-target and target-to-source translation applications.
    Type: Grant
    Filed: March 27, 2003
    Date of Patent: November 18, 2008
    Assignee: University of Southern California
    Inventors: Daniel Marcu, William Wong, Kevin Knight, Philipp Koehn
  • Task parallelization in a text-to-text system
    Patent number: 7389222
    Abstract: Parallelization of word alignment for a text-to-text operation. The training data is divided into multiple groups, and training is carried out of each group on separate processors. Different techniques can be carried out to increase the speed of the processing. The hookups can be done only once for all of multiple different iterations. Moreover, parallel operations can apply only to the counts, since this may be the most time-consuming part.
    Type: Grant
    Filed: April 26, 2006
    Date of Patent: June 17, 2008
    Assignee: Language Weaver, Inc.
    Inventors: Greg Langmead, Kenji Yamada, Kevin Knight, Daniel Marcu
  • Named entity translation
    Publication number: 20080114583
    Abstract: Translating named entities from a source language to a target language. In general, in one implementation, the technique includes: generating potential translations of a named entity from a source language to a target language using a pronunciation-based and spelling-based transliteration model, searching a monolingual resource in the target language for information relating to usage frequency, and providing output including at least one of the potential translations based on the usage frequency information.
    Type: Application
    Filed: June 7, 2007
    Publication date: May 15, 2008
    Inventors: Yaser Al-Onaizan, Kevin Knight
  • Statistical translation using a large monolingual corpus
    Patent number: 7340388
    Abstract: A statistical machine translation (MT) system may use a large monolingual corpus to improve the accuracy of translated phrases/sentences. The MT system may produce a alternative translations and use the large monolingual corpus to (re)rank the alternative translations.
    Type: Grant
    Filed: March 26, 2003
    Date of Patent: March 4, 2008
    Assignee: University of Southern California
    Inventors: Radu Soricut, Daniel Marcu, Kevin Knight
  • Named entity translation
    Patent number: 7249013
    Abstract: Translating named entities from a source language to a target language. In general, in one implementation, the technique includes: generating potential translations of a named entity from a source language to a target language using a pronunciation-based and spelling-based transliteration model, searching a monolingual resource in the target language for information relating to usage frequency, and providing output including at least one of the potential translations based on the usage frequency information.
    Type: Grant
    Filed: March 11, 2003
    Date of Patent: July 24, 2007
    Assignee: University of Southern California
    Inventors: Yaser Al-Onaizan, Kevin Knight
  • Language capability assessment and training apparatus and techniques
    Publication number: 20070122792
    Abstract: A learning system for a text-to-text application such as a machine translation system. The system has questions, and a matrix of correct answers to those questions. Any of the many different correct answers within the matrix can be considered as perfectly correct answers to the question. The system operates by displaying a question, which may be a phrase to be translated, and obtaining an answer to the question from the user. The answer is compared against the matrix and scored. Feedback may also be provided to the user.
    Type: Application
    Filed: November 9, 2005
    Publication date: May 31, 2007
    Inventors: Michel Galley, Kevin Knight, Daniel Marcu
  • Adapter for allowing both online and offline training of a text to text system
    Publication number: 20070094169
    Abstract: An adapter for a text to text training. A main corpus is used for training, and a domain specific corpus is used to adapt the main corpus according to the training information in the domain specific corpus. The adaptation is carried out using a technique that may be faster than the main training. The parameter set from the main training is adapted using the domain specific part.
    Type: Application
    Filed: September 9, 2005
    Publication date: April 26, 2007
    Inventors: Kenji Yamada, Kevin Knight, Greg Langmead
  • Integer programming decoder for machine translation
    Patent number: 7177792
    Abstract: A machine translation (MT) decoder may transform a translation problem into an integer programming problem, such as a Traveling Salesman Problem (TSP). The decoder may invoke an integer program (IP) solver to solve the integer programming problem and output a likely decoding based on the solution.
    Type: Grant
    Filed: May 31, 2002
    Date of Patent: February 13, 2007
    Assignee: University of Southern California
    Inventors: Kevin Knight, Kenji Yamada
  • Identifying documents which form translated pairs, within a document collection
    Publication number: 20070033001
    Abstract: A training system for text to text application. The training system finds groups of documents, and identifies automatically similar documents in the groups which are similar. The automatically identified documents can then be used for training of the text to text application. The comparison uses reduced size versions of the documents in order to minimize the amount of processing.
    Type: Application
    Filed: August 3, 2005
    Publication date: February 8, 2007
    Inventors: Ion Muslea, Kevin Knight, Daniel Marcu
  • Integer programming decoder for machine translation
    Publication number: 20060195312
    Abstract: A machine translation (MT) decoder may transform a translation problem into an integer programming problem, such as a Traveling Salesman Problem (TSP). The decoder may invoke an integer program (IP) solver to solve the integer programming problem and output a likely decoding based on the solution.
    Type: Application
    Filed: April 28, 2006
    Publication date: August 31, 2006
    Inventors: Kevin Knight, Kenji Yamada
  • Training for a text-to-text application which uses string to tree conversion for training and decoding
    Publication number: 20060142995
    Abstract: Training and translation using trees and/or subtrees as parts of the rules. A target language is word aligned with a source language, and at least one of the languages is parsed into trees. The trees are used for training, by aligning conversion steps, forming a manual set of information representing the conversion steps and then learning rules from that reduced set. The rules include subtrees as parts thereof, and are used for decoding, along with an n-gram language model and a syntax based language mode.
    Type: Application
    Filed: October 12, 2005
    Publication date: June 29, 2006
    Inventors: Kevin Knight, Michel Galley, Mark Hopkins, Daniel Marcu, Ignacio Thayer
  • Training tree transducers
    Publication number: 20050234701
    Abstract: Training using tree transducers is described. Given sample input/output pairs as training, and given a set of tree transducer rules, the information is combined to yield locally optimal weights for those rules. This combination is carried out by building a weighted derivation forest for each input/output pair and applying counting methods to those forests.
    Type: Application
    Filed: March 15, 2005
    Publication date: October 20, 2005
    Inventors: Jonathan Graehl, Kevin Knight
  • Sentence generator
    Publication number: 20040034520
    Abstract: Systems and techniques for generating language from an input use a symbolic generator and a statistical ranker. The symbolic generator may use a transformation algorithm to transform one or more portions of the input. For example, mapping rules such as morph rules, recasting rules, filling rules, and/or ordering rules may be used. The symbolic generator may output a plurality of possible expressions, while the statistical ranker may rank at least some of the possible expressions to determine the best output.
    Type: Application
    Filed: March 4, 2003
    Publication date: February 19, 2004
    Inventors: Irene Langkilde-Geary, Kevin Knight
  • Phrase to phrase joint probability model for statistical machine translation
    Publication number: 20040030551
    Abstract: A machine translation (MT) system may utilize a phrase-based joint probability model. The model may be used to generate source and target language sentences simultaneously. In an embodiment, the model may learn phrase-to-phrase alignments from word-to-word alignments generated by a word-to-word statistical MT system. The system may utilize the joint probability model for both source-to-target and target-to-source translation applications.
    Type: Application
    Filed: March 27, 2003
    Publication date: February 12, 2004
    Inventors: Daniel Marcu, William Wong, Kevin Knight, Philipp Koehn
  • Statistical machine translation
    Publication number: 20040024581
    Abstract: A method includes detecting a syntactic chunk in a source string in a first language, assigning a syntactic label to the detected syntactic chunk in the source string, mapping the detected syntactic chunk in the source string to a syntactic chunk in a target string in a second language, said mapping based on the assigned syntactic label, and translating the source string into a possible translation in the second language.
    Type: Application
    Filed: March 28, 2003
    Publication date: February 5, 2004
    Inventors: Philipp Koehn, Kevin Knight
  • Statistical translation using a large monolingual corpus
    Publication number: 20030233222
    Abstract: A statistical machine translation (MT) system may use a large monolingual corpus to improve the accuracy of translated phrases/sentences. The MT system may produce a alternative translations and use the large monolingual corpus to (re)rank the alternative translations.
    Type: Application
    Filed: March 26, 2003
    Publication date: December 18, 2003
    Inventors: Radu Soricut, Daniel Marcu, Kevin Knight
  • Constructing a translation lexicon from comparable, non-parallel corpora
    Publication number: 20030204400
    Abstract: A machine translation system may use non-parallel monolingual corpora to generate a translation lexicon. The system may identify identically spelled words in the two corpora, and use them as a seed lexicon. The system may use various clues, e.g., context and frequency, to identify and score other possible translation pairs, using the seed lexicon as a basis. An alternative system may use a small bilingual lexicon in addition to non-parallel corpora to learn translations of unknown words and to generate a parallel corpus.
    Type: Application
    Filed: March 26, 2003
    Publication date: October 30, 2003
    Inventors: Daniel Marcu, Kevin Knight, Dragos Stefan Munteanu, Philipp Koehn
  • Named entity translation
    Publication number: 20030191626
    Abstract: Translating named entities from a source language to a target language. In general, in one implementation, the technique includes: generating potential translations of a named entity from a source language to a target language using a pronunciation-based and spelling-based transliteration model, searching a monolingual resource in the target language for information relating to usage frequency, and providing output including at least one of the potential translations based on the usage frequency information.
    Type: Application
    Filed: March 11, 2003
    Publication date: October 9, 2003
    Inventors: Yaser Al-Onaizan, Kevin Knight
  • Syntax-based statistical translation model
    Publication number: 20030023423
    Abstract: A statistical translation model (TM) may receive a parse tree in a source language as an input and separate output a string in a target language. The TM may perform channel operations on the parse tree using model parameters stored in probability tables. The channel operations may include reordering child nodes, inserting extra words at each node, e.g., NULL words, translating leaf words, and reading off leaf words to generate the string in the target language. The TM may assign a translation probability to the string in the target language.
    Type: Application
    Filed: July 3, 2002
    Publication date: January 30, 2003
    Inventors: Kenji Yamada, Kevin Knight