Machine translation method and apparatus

Patent metadata

Field	Value
Publication number	US-2018052829-A1
Application number	US-201715429709-A
Country	US
Kind code	A1
Filing date	Feb 10, 2017
Priority date	Aug 16, 2016
Publication date	Feb 22, 2018
Grant date	—

Abstract

A machine translation method and apparatus are provided. The machine translation apparatus generates a feature vector of a source sentence from the source sentence, where the source sentence being is written in a first language, and converts the generated feature vector of the source sentence to a feature vector of a normalized sentence. The machine translation apparatus generates a target sentence from the feature vector of the normalized sentence, wherein the target sentence corresponding corresponds to the source sentence and being is written in a second language.

First claim

What is claimed is:

1 . A machine translation method, comprising:
generating, at a processor, a feature vector of a source sentence, wherein the source sentence is written in a first language; converting, at the processor, the feature vector of the source sentence to a feature vector of a normalized sentence; and generating, at the processor, a target sentence from the feature vector of the normalized sentence, wherein the target sentence corresponds to the source sentence and is written in a second language.

2 . The machine translation method of claim 1 , wherein the feature vector of the normalized sentence is a closest feature vector to the generated feature vector of the source sentence, among pre-determined feature vectors of normalized sentences.

3 . The machine translation method of claim 1 , wherein the normalized sentence comprises any one or any combination of any two or more of a vocabulary, a morpheme, or a symbol omitted from the source sentence.

4 . The machine translation method of claim 1 , wherein the normalized sentence is a sentence generated by a substitution of any one or any combination of two or more of a morpheme, a vocabulary, a word, or a phrase included in the source sentence.

5 . The machine translation method of claim 1 , wherein the normalized sentence is a sentence generated by changing word spacing in the source sentence.

6 . The machine translation method of claim 1 , wherein the normalized sentence is a sentence generated by changing a word order in the source sentence.

7 . The machine translation method of claim 1 , wherein the source sentence is a sentence generated by recognizing a voice signal in the first language received from a user.

8 . A machine translation method, comprising:
generating, at a processor, a feature vector of a source sentence, wherein the source sentence is written in a first language; converting, at the processor, the feature vector of the source sentence to a feature vector of a target sentence, wherein the target sentence is written in a second language; and generating, at the processor, a normalized sentence from the feature vector of the target sentence by transforming the target sentence.

9 . The machine translation method of claim 8 , wherein the generating of the normalized sentence comprises:
selecting a closest feature vector to the feature vector of the target sentence from feature vectors of pre-determined normalized sentences; and generating the normalized sentence from the selected feature vector.

10 . The machine translation method of claim 8 , wherein the normalized sentence is a sentence generated by any one or any combination of two or more of omitting a vocabulary, a morpheme and a symbol from the target sentence, substituting a vocabulary and a morpheme in the target sentence, or changing word spacing and a word order in the target sentence.

11 . A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform the method of claim 1 .

12 . A machine translation apparatus, comprising:
a memory comprising a neural network; and a processor configured to
generate a feature vector of a source sentence,
convert the generated feature vector of the source sentence to a feature vector of a normalized sentence, and
generate a target sentence from the feature vector of the normalized sentence, based on the neural network, wherein the source sentence is written in a first language, and the target sentence corresponding to the source sentence is written in a second language.

13 . The machine translation apparatus of claim 12 , wherein the feature vector of the normalized sentence is a closest feature vector to the generated feature vector of the source sentence among feature vectors of pre-determined normalized sentences.

14 . The machine translation apparatus of claim 12 , wherein the normalized sentence is a sentence generated by a substitution of any one or any combination of any two or more of a morpheme, a vocabulary, a word, or a phrase included in the source sentence.

15 . The machine translation apparatus of claim 12 , wherein the normalized sentence is a sentence generated by changing word spacing in the source sentence.

16 . The machine translation apparatus of claim 12 , wherein the normalized sentence is a sentence generated by changing a word order in the source sentence.

17 . The machine translation apparatus of claim 12 , wherein the source sentence is a sentence generated by recognizing a voice signal in the first language received from a user.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Lee Hodong

Classifications

• G06N3/048

  Activation functions · CPC title

• G06N3/045

  Combinations of networks · CPC title

• G06N3/08 Primary

  Learning methods · CPC title

• G06F40/42

  Data-driven translation · CPC title

• G06F40/268

  Morphological analysis · CPC title