Patents by Inventor Philipp Koehn

Philipp Koehn 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).

  • Statistical noun phrase translation
    Patent number: 8548794
    Abstract: A statistical machine translation (MT) system may include a noun phrase/prepositional phrase (NP/PP) translation subsystem to translation NP/PPs as a subtask in an MT operation. The NP/PP translation subsystem may use a model trained on an NP/PP corpus and a decoder to generate an n-best list of candidate translations and a re-ranker to re-rank the candidate translations based on a machine learning method and additional features based on known properties of NP/PPs.
    Type: Grant
    Filed: July 2, 2004
    Date of Patent: October 1, 2013
    Assignee: University of Southern California
    Inventor: Philipp Koehn
  • Building a translation lexicon from comparable, non-parallel corpora
    Patent number: 8234106
    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: Grant
    Filed: October 8, 2009
    Date of Patent: July 31, 2012
    Assignee: University of Southern California
    Inventors: Daniel Marcu, Kevin Knight, Dragos Stefan Munteanu, Philipp Koehn
  • Empirical Methods for Splitting Compound Words with Application to Machine Translation
    Publication number: 20100174524
    Abstract: A statistical machine translation (MT) system may include a compound splitting module to split compounded words for more accurate translation. The compound splitting module select a best split for translation by the MT system.
    Type: Application
    Filed: March 11, 2010
    Publication date: July 8, 2010
    Inventor: Philipp Koehn
  • Empirical methods for splitting compound words with application to machine translation
    Patent number: 7711545
    Abstract: A statistical machine translation (MT) system may include a compound splitting module to split compounded words for more accurate translation. The compound splitting module select a best split for translation by the MT system.
    Type: Grant
    Filed: July 2, 2004
    Date of Patent: May 4, 2010
    Assignee: Language Weaver, Inc.
    Inventor: Philipp Koehn
  • Statistical machine translation
    Patent number: 7624005
    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: Grant
    Filed: March 28, 2003
    Date of Patent: November 24, 2009
    Assignee: University of Southern California
    Inventors: Philipp Koehn, Kevin Knight
  • Constructing a translation lexicon from comparable, non-parallel corpora
    Patent number: 7620538
    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: Grant
    Filed: March 26, 2003
    Date of Patent: November 17, 2009
    Assignee: University of Southern California
    Inventors: Daniel Marcu, Kevin Knight, Dragos Stefan Munteanu, Philipp Koehn
  • 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
  • Statistical noun phrase translation
    Publication number: 20050038643
    Abstract: A statistical machine translation (MT) system may include a noun phrase/prepositional phrase (NP/PP) translation subsystem to translation NP/PPs as a subtask in an MT operation. The NP/PP translation subsystem may use a model trained on an NP/PP corpus and a decoder to generate an n-best list of candidate translations and a re-ranker to re-rank the candidate translations based on a machine learning method and additional features based on known properties of NP/PPs.
    Type: Application
    Filed: July 2, 2004
    Publication date: February 17, 2005
    Inventor: Philipp Koehn
  • Empirical methods for splitting compound words with application to machine translation
    Publication number: 20050033565
    Abstract: A statistical machine translation (MT) system may include a compound splitting module to split compounded words for more accurate translation. The compound splitting module select a best split for translation by the MT system.
    Type: Application
    Filed: July 2, 2004
    Publication date: February 10, 2005
    Inventor: Philipp Koehn
  • 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
  • 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