Machine translation apparatus and machine translation method

• US 10,311,147 B2
• Filed: 02/15/2017
• Issued: 06/04/2019
• Est. Priority Date: 03/14/2016
• Status: Active Grant

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Sumita, Kazuo, Sonoo, Satoshi
• Primary Examiner(s): Dorvil, Richemond
• Assistant Examiner(s): Chavez, Rodrigo A
• Application Number:
  US15/433,423
• Publication Number:
  US 20170262434A1
• Time in Patent Office: 839 Days
• Field of Search: 704 2, 704 4, 704 7, 704 8, 704 9, 704251, 704257, 704270, 7042701, 704275
• CPC Class Codes: G06F 16/243 Natural language query formulation
• CPC Class Codes: G06F 16/2455 Query execution
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

According to one embodiment, a machine translation apparatus includes the following elements. The machine translation unit performs machine translation on a first text in a first language to generate a first machine translation result in a second language. The retrieval unit retrieves a first question sentence in the first language similar to the first text to obtain a degree of similarity between the first text and the first question sentence. The determination unit determines a first answer sentence in the first language corresponding to the first question sentence to be an output target when the degree of similarity is higher than a threshold and determines the first machine translation result to be an output target when the degree of similarity is lower than the threshold.

Claims

1. A machine translation apparatus comprising:

a memory configured to store question sentences in a first language, answer sentences in the first language, and location information items indicative of a location of a destination in association with one another; and

processing circuitry electrically coupled to the memory, the processing circuitry being configured to;

perform machine translation on a first text in the first language to generate a first machine translation result in a second language;

retrieve a first question sentence in the first language similar to the first text from the memory to obtain a degree of similarity between the first text and the first question sentence;

determine a first answer sentence in the first language corresponding to the first question sentence to be an output target when the degree of similarity is higher than a threshold and determine the first machine translation result to be an output target when the degree of similarity is equal to or lower than the threshold; and

determine, when newly registering a question sentence, an answer sentence, and a location information item in the memory in association with one another, whether or not a question sentence is present which is similar to the new question sentence and which is associated with another location information item different from the new location information item, and register the new question sentence, the new answer sentence, and the other location information item in the memory in association with one another when no question sentence is present which is similar to the new question sentence and which is associated with the other location information item different from the new location information item.

2. The machine translation apparatus according to claim 1, wherein the processing circuitry is further configured to register the question sentences, the answer sentences, and the location information items in the memory.

3. The machine translation apparatus according to claim 2, wherein the processing circuitry is further configured to register the first machine translation result in the memory when the first text includes a question sentence and an answer sentence.

4. The machine translation apparatus according to claim 1, wherein the processing circuitry is further configured to perform speech recognition on a first speech signal to generate the first text.

5. The machine translation apparatus according to claim 4, wherein the processing circuitry is further configured to:

perform speech recognition on a second speech signal in the second language different from the first speech signal to generate a second text in the second language; and

perform machine translation on the second text in the second language to generate a second machine translation result in the first language.

6. The machine translation apparatus according to claim 1, wherein the processing circuitry is further configured to:

perform machine translation on a second text in the second language different from the first text to generate a second machine translation result in the first language; and

register the second machine translation result in the memory when the second text includes a question sentence and an answer sentence.

7. A machine translation apparatus comprising:

a memory configured to store question sentences in a second language, answer sentences in the second language, and location information items indicative of a location of a destination in association with one another; and

processing circuitry electrically coupled to the memory, the processing circuitry being configured to;

perform machine translation on a first text in a first language to generate a first machine translation result in the second language;

retrieve a first question sentence in the second language similar to the first machine translation result from the memory to obtain a degree of similarity between the first machine translation result and the first question sentence;

determine a translated sentence in the first language for a first answer sentence in the second language corresponding to the first question sentence to be an output target when the degree of similarity is higher than a threshold and determine the first machine translation result to be an output target when the degree of similarity is equal to or lower than the threshold; and

determine, when newly registering a question sentence, an answer sentence, and a location information item in the memory in association with one another, whether or not a question sentence is present which is similar to the new question sentence and which is associated with another location information item different from the new location information item, and register the new question sentence, the new answer sentence, and the other location information item in the memory in association with one another when no question sentence is present which is similar to the new question sentence and which is associated with the other location information item different from the new location information item.

8. The machine translation apparatus according to claim 7, wherein the processing circuitry is further configured to perform machine translation on the first answer sentence in the second language to generate the translated sentence in the first language.

9. The machine translation apparatus according to claim 7, wherein the processing circuitry is further configured to register the question sentences, the answer sentences, and the location information items in the memory.

10. The machine translation apparatus according to claim 9, wherein the processing circuitry is further configured to register the first machine translation result in the storage when the first text includes a question sentence and an answer sentence.

11. The machine translation apparatus according to claim 7, wherein the processing circuitry is further configured to perform speech recognition on a first speech signal to generate the first text.

12. The machine translation apparatus according to claim 11, wherein the processing circuitry is further configured to:

perform speech recognition on a second speech signal in the second language different from the first speech signal to generate a second text in the second language; and

perform machine translation on the second text in the second language to generate a second machine translation result in the first language.