US 10,380,243 B2Granted

Parallel-translation dictionary creating apparatus and method

AssigneeFujitsu Limited

InventorsYuchang Cheng, Nobuyuki Katae, Tomoki Nagase

Life of this patent

Estimating the term…

Loading patent…

Abstract

A parallel-translation dictionary creating apparatus that includes a processor configured to create a parallel-translation dictionary; the processor extracts words from each of the plurality of documents; performs an estimation and storage of a semantic classification of the extracted words; based on a result of the estimation of the semantic classification for the word in the document that is a current processing target and the word pair registered in the parallel-translation word list; updates, to the semantic classification of the word for which the semantic classification has been estimated, the semantic classification of a corresponding word that corresponds to the word and to the subject matter of the document that is the current processing target; and creates the parallel-translation dictionary based on the semantic classification of the word obtained by the estimation of the semantic classification of the word and the update of the semantic classification of the corresponding word.

Claims16

Dependent claims

A parallel-translation dictionary creating apparatus comprising:

a memory configured to store a parallel-translation word list in which one or more word pairs for which a parallel translation relationship across a plurality of languages has been confirmed and a semantic classification of a word;
and
a processor connected to the memory and configured to create a parallel-translation dictionary in which the parallel translation relationship for words across the plurality of languages is registered, based on a plurality of documents that are written in the plurality of languages and which contain a corresponding subject matter, the parallel-translation word list, and the semantic classification of words, wherein
the processor executes processes including:
performing a morphological analysis with respect to each of a plurality of documents that are written in a plurality of languages and which contain a corresponding subject matter, and extracting words from each of the plurality of documents;
with respect to each of the plurality of documents, performing an estimation of the semantic classification of the extracted words and making the memory store the semantic classification of the word;
based on a result of the estimation of the semantic classification for the word in a target document that is a current processing target and the one or more word pairs registered in the parallel-translation word list, performing an update for updating, to the semantic classification of the word for which the semantic classification has been estimated, the semantic classification of a corresponding word that corresponds to the word for which the semantic classification has been estimated and that is in a document of another language which contains a subject matter that corresponds to a subject matter of the target document that is the current processing target;
controlling the estimation of the semantic classification of the word and the update of the semantic classification of the corresponding word;
creating the parallel-translation dictionary based on the semantic classification of the word obtained by the estimation of the semantic classification of the word and the update of the semantic classification of the corresponding word;
receiving a document to be translated from a terminal device;
utilizing the created parallel-translation dictionary to translate the document;
and
outputting the translated document to the terminal device.

10 more elements

A parallel-translation dictionary creation method comprising:

by a computer, performing a morphological analysis with respect to each of a plurality of documents that are written in a plurality of languages and which contain a corresponding subject matter and extracting words from each of the plurality of documents;
by the computer, repeating a plurality of times a process of performing an estimation and storage of a semantic classification of the extracted words with respect to each of the plurality of documents, and based on a result of the estimation of the semantic classification for the word in a target document that is a current processing target and one or more word pairs that are registered in a parallel-translation word list and for which a parallel translation relationship across the plurality of languages has been confirmed, performing an update for updating, to the semantic classification of the word for which the semantic classification has been estimated, the semantic classification of a corresponding word that corresponds to the word for which the semantic classification has been estimated and that is in a document of another language which contains the subject matter that corresponds to the subject matter of the target document that is the current processing target;
by the computer, creating a parallel-translation dictionary in which a parallel translation relationship for words across the plurality of languages is registered, based on the semantic classification of the word obtained by the process of performing the estimation of the semantic classification of the word and the process of performing the update of the semantic classification;
receiving, by the computer, a document to be translated from a terminal device;
utilizing, by the computer, the created parallel-translation dictionary to translate the document;
and
outputting, by the computer, the translated document to the terminal device.

4 more elements

A non-transitory computer-readable recording medium having stored therein a program that causes a computer to execute a process for creating a parallel-translation dictionary in which a parallel translation relationship for words across a plurality of languages is registered, the process comprising:

performing a morphological analysis with respect to each of a plurality of documents that are written in a plurality of languages and which contain a corresponding subject matter and extracting words from each of the plurality of documents;
repeating a plurality of times a process of performing an estimation and storage of a semantic classification of the extracted words with respect to each of the plurality of documents, and based on a result of the estimation of the semantic classification for the word in a target document that is a current processing target and one or more word pairs that are registered in a parallel-translation word list and for which a parallel translation relationship across the plurality of languages has been confirmed, performing an update for updating, to the semantic classification of the word for which the semantic classification has been estimated, the semantic classification of a corresponding word that corresponds to the word for which the semantic classification has been estimated and that is in a document of another language which contains the subject matter that corresponds to the subject matter of the target document that is the current processing target;
creating a parallel-translation dictionary in which a parallel translation relationship for words across the plurality of languages is registered, based on the semantic classification of the word obtained by the process of performing the estimation of the semantic classification of the word and the process of performing the update of the semantic classification;
receiving a document to be translated from a terminal device;
utilizing the created parallel-translation dictionary to translate the document;
and
outputting the translated document to the terminal device.

4 more elements

Dependencies are inferred from the claim text.