University of Southern California

Language Weaver, Inc.

Philipp Koehn

Kevin Knight

Daniel Marcu

Dragos Stefan Munteanu

William Wong

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.

Statistical noun phrase translation

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.

Building a translation lexicon from comparable, non-parallel corpora

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.

Empirical methods for splitting compound words with application to machine translation

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.

Statistical machine translation

Constructing a translation lexicon from comparable, non-parallel corpora

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.

Growing community of inventors

Venice, CA, United States of America

Philipp Koehn