APPARATUS AND METHOD FOR PROVIDING TWO-WAY AUTOMATIC INTERPRETATION AND TRANSLATION SERVICE

• US 20130297285A1
• Filed: 04/16/2013
• Published: 11/07/2013
• Est. Priority Date: 05/02/2012
• Status: Active Grant

• Current Assignee: Electronics and Telecommunications Research Institute
• Original Assignee: Electronics and Telecommunications Research Institute
• Inventors: JIN, Yun, KWON, Oh-Woog, LEE, Ki-Young, CHOI, Sung-Kwon, ROH, Yoon-Hyung, PARK, Eun-Jin, KIM, Young-Kil, PARK, Sang-Kyu
• Granted Patent: US 9,058,322 B2
• Time in Patent Office: Days
• US Class Current: 704/2
• CPC Class Codes: G06F 40/53 Processing of non-Latin text kana-to-kanji conversion G06F40/129; vowelisation G06F40/232
• CPC Class Codes: G06F 40/55 Rule-based translation
• 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

Abstract

The present invention relates to an apparatus and method for providing a two-way automatic interpretation and translation service. The apparatus includes a first interpretation and translation unit for interpreting and translating a first language into a second language. A second interpretation and translation unit interprets and translates the second language into the first language. A context information management unit receives conversational context and translation history information, and shares and manages the conversational context and translation history information. Each of the first and second interpretation and translation units provides an interpretation service for receiving an input conversation in the first or second language in speech and outputting results of interpretation in speech in the second or first language, and a translation service for receiving an input conversation in the first or second language in text and outputting results of translation in text in the second or first language.

Claims

1. An apparatus for providing a two-way automatic interpretation and translation service, comprising:

a first interpretation and translation unit for interpreting and translating a first language into a second language;

a second interpretation and translation unit for interpreting and translating the second language into the first language; and

a context information management unit for receiving conversational context and translation history information processed when translation is performed from the first and second interpretation and translation units, and sharing and managing the conversational context and translation history information,

wherein each of the first and second interpretation and translation units provides an interpretation service for receiving an input conversation in the first language or the second language in a form of speech and outputting results of interpretation of the input conversation in the form of speech in the second language or the first language, and a translation service for receiving an input conversation in the first language or the second language in a form of text and outputting results of translation of the input conversation in a form of text in the second language or the first language.

2. The apparatus of claim 1, wherein the first interpretation and translation unit comprises:

a first speech recognition module for receiving an input conversation of a first language user in the form of speech, receiving an context of conversation and an information of translation history information from the context information management unit and converting the input conversation into text in the first language;

a first morphological analysis module for receiving the first language text, receiving an context of conversation and an information of translation history information from the context information management unit, separating sentences and words from the input text and tagging each separated word with part-of-speech tags;

a first syntactic analysis module for receiving part-of-speech tags and an context of conversation and an information of translation history information from the context information management unit, setting syntactic relationships between the words, and generating a first language syntactic tree indicative of results of the setting;

a first transfer module for receiving the generated first language syntactic tree and an context of conversation and an information of translation history information from the context information management unit, converting the first language syntactic tree into a second language syntactic tree, and translating first language vocabularies corresponding to a terminal node into second language vocabularies; and

a first generation module for receiving the second language vocabularies, receiving an context of conversation and an information of translation history information from the context information management unit and generating second language sentences from the second language vocabularies.

3. The apparatus of claim 2, wherein the first interpretation and translation unit further comprises:

a first translation information output module for outputting the generated second language sentences in the form of text; and

a first speech synthesis module for outputting the generated second language sentences in the form of speech.

4. The apparatus of claim 1, wherein the second interpretation and translation unit comprises:

a second speech recognition module for receiving an input conversation of a second language user in the form of speech, receiving an context of conversation and an information of translation history information from the context information management unit and converting the input conversation into text in the second language;

a second morphological analysis module for receiving the second language text, receiving an context of conversation and an information of translation history information from the context information management unit and separating sentences and words from the input text, tagging each separated word with part-of-speech tags;

a second syntactic analysis module for receiving part-of-speech tags and an context of conversation and an information of translation history information from the context information management unit, setting syntactic relationships between the words, and generating a second language syntactic tree indicative of results of the setting;

a second transfer module for receiving the generated second language syntactic tree and an context of conversation and an information of translation history information from the context information management unit, converting the second language syntactic tree into a first language syntactic tree, and translating second language vocabularies corresponding to a terminal node into first language vocabularies, and

a second generation module for receiving the first language vocabularies, receiving an context of conversation and an information of translation history information from the context information management unit and generating first language sentences from the first language vocabularies.

5. The apparatus of claim 4, wherein the second interpretation and translation unit further comprises:

a second translation information output module for outputting the generated first language sentences in the form of text; and

a second speech synthesis module for outputting the generated second language sentences in the form of speech.

6. The apparatus of claim 1, wherein the context information management unit comprises:

a first language-second language context processing module for managing conversational context and translation history information analyzed and processed by the first interpretation and translation unit; and

a second language-first language context processing module for managing conversational context and translation history information analyzed and processed by the second interpretation and translation unit.

7. The apparatus of claim 1, further comprising a two-way communication unit disposed between the first and second interpretation and translation units and the context information management unit and configured to perform mutual communication therebetween so as to collect and provide conversational context and translation history information.

8. The apparatus of claim 7, further comprising a context history management unit for storing tire conversational context and the translation history information received from the two-way communication unit in a context translation information database (DB), searching the context translation information DB for information required to process context by the context information management unit, and transferring found information.

9. A method of providing a two-way automatic interpretation and translation service, comprising:

providing an interpretation service for receiving an input conversation in a first language or a second language in a form of speech and outputting results of interpretation of the input conversation in a form of speech in the second language or the first language, and a translation service for receiving an input conversation in the first language or the second language in a form of text and outputting results of translation of the input conversation in a form of text in the second language or the first language, using a first interpretation and translation unit or a second interpretation and translation unit; and

sharing and managing, by a context information management unit receiving conversational context and translation history information processed when translation is performed from the first and second interpretation and translation units, the conversational context and the translation history information.

10. The method of claim 9, wherein the providing the interpretation and translation service using the first interpretation and translation unit is configured, to receive an input conversation of a first language user in the form of speech, receive an context of conversation and an information of translation history information from a context information management unit and converts the conversation into text in tire first language, separate sentences and words from the input text, and tag each separated word with part-of-speech tags, and sets syntactic relationships between the words, and generates a first language syntactic tree indicative of results of the setting, and converts the first language syntactic free into a second language syntactic tree, and translates first language vocabularies corresponding to a terminal node into second language vocabularies and generates second language sentences from the second language vocabularies.

11. The method of claim 9, wherein the providing the interpretation and translation service using the second interpretation and translation unit is configured to receive an input conversation of a second language user in the form of speech, receive an context of conversation and an information of translation history information from a context information management unit and converts the conversation into text in the first language, separate sentences and words from the input text, and tag each separated word with part-of-speech tags, and sets syntactic relationships between the words, and generates a second language syntactic tree indicative of results of the setting, and converts the second language syntactic tree into a first language syntactic tree, and translates second language vocabularies corresponding to a terminal node into first language vocabularies and generates first language sentences from the first language vocabularies.

12. The method of claim 9, wherein the sharing and managing the conversational context and the translation history information analyzed and processed by the first and second interpretation and translation units is configured to searches the context translation information DB for information required to process context by the first and second interpretation and translation units, and transfers the found information.