Xerox Corporation

National Research Council of Canada

Michel Simard

Cyril Goutte

Eric Gaussier

Kenji Yamada

Marc Dymetman

Nicola Cancedda

Roland Kuhn

Bruno Cavestro

Veronika Lux-Pogodalla

Pierre Isabelle

Arne Mauser

This application is related to a means and a method for facilitating the use of translation memories by aligning words of an input source language sentence with the correspondent translated words in target language sentence. More specifically, this invention relates to such a means and method where there is an enhanced translation memory comprising an alignment function.

Method and system for using alignment means in matching translation

In a translation apparatus, a translation memory () stores (i) source language target language translation unit pairs and (ii) structural information for at least some source language translation units indicating a structural position within a document from which the source language translation unit was derived. A comparator () compares a new source language translation unit with source language translation units stored in the translation memory. Each comparison includes (i) a textual comparison and (ii) a structural comparison between an identified structural position within a source language document () from which the new source language translation unit was derived and the structural information for the source language translation unit stored in the translation memory.

Retrieval method for translation memories containing highly structured documents

Methods are disclosed for performing proper word alignment that satisfy constraints of coverage and transitive closure. Initially, a translation matrix which defines word association measures between source and target words of a corpus of bilingual translations of source and target sentences is computed. Subsequently, in a first method, the association measures in the translation matrix are factorized and orthogonalized to produce cepts for the source and target words, which resulting matrix factors may then be, optionally, multiplied to produce an alignment matrix. In a second method, the association measures in the translation matrix are thresholded, and then closed by transitivity, to produce an alignment matrix, which may then be, optionally, factorized to produce cepts. The resulting cepts or alignment matrices may then be used by any number of natural language applications for identifying words that are properly aligned.

Apparatus and methods for aligning words in bilingual sentences

A machine translation method for translating source text from a first language to target text in a second language includes receiving the source text in the first language and accessing a library of bi-fragments, each of the bi-fragments including a text fragment from the first language and a text fragment from the second language, at least some of the bi-fragments comprising non-contiguous bi-fragments in which at least one of the text fragment from the first language and the text fragment from the second language comprises a non-contiguous fragment.

Machine translation using non-contiguous fragments of text

Growing community of inventors

Gatineau, Canada

Michel Simard