TRANSLATION SYSTEM INFORMATION EXTRACTION

• US 20150046147A1
• Filed: 10/23/2014
• Published: 02/12/2015
• Est. Priority Date: 04/15/2008
• Status: Abandoned Application

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Waibel, Alexander, Lane, Ian R.
• Application Number:
  US14/522,164
• Publication Number:
  US 20150046147A1
• Time in Patent Office: Days
• US Class Current: 704/2
• CPC Class Codes: G06F 40/44 Statistical methods, e.g. probability models
• 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 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 15/06 Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice G10L15/14 takes precedence
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/0631 Creating reference templates; Clustering

Abstract

A speech translation system and methods are disclosed for cross-lingual communication that enable users to improve and modify content and usage of the system and easily abort or reset translation. The system includes a speech recognition module configured for accepting an utterance, a machine translation module, an interface configured to communicate the utterance and proposed translation, a correction module and an abort action unit that removes any hypotheses or partial hypotheses and terminates translation. The system also includes modules for information extraction based on keywords in the received or translated speech.

Claims

1. A method comprising:

receiving from a user, an utterance in a first language;

translating, by a speech translation system, the utterance in the first language into a second language;

extracting, by the speech translation system, one or more keywords from the utterance, the keywords indicative of a topic;

retrieving additional information related to the topic, based at least in part on the extracted keywords; and

presenting to the user the additional information related to the topic.

2. The method of claim 1, wherein the keywords are extracted based on their frequency and context.

3. The method of claim 1, wherein the extracted keywords may be in the utterance in the first language or the translated utterance in the second language.

4. The method of claim 1, wherein the extracted keywords may be words or phrases.

5. The method of claim 1, wherein the keywords are extracted from system logs storing the utterance.

6. The method of claim 1, wherein the additional information related to the topic is retrieved from a third party source.

7. The method of claim 1, wherein presenting to the user the additional information related to the topic further comprises presenting the additional information in both the first and second languages.

8. The method of claim 1, wherein presenting to the user the additional information related to the topic further comprises presenting targeted advertisements related to the topic.

9. The method of claim 1, wherein presenting to the user the additional information related to the topic further comprises presenting supportive information associated with the topic.

10. The method of claim 1, wherein the user is communicating with another user using bi-directional translation.

11. The method of claim 1, further comprising:

displaying simultaneously in text, on a user interface display of the speech translation system, at least (i) the received utterance in the first language, and (ii) the translation into the second language of the utterance.

12. The method of claim 1, wherein translating the utterance in the first language into the second language comprises generating a translation in the second language via either a rule-based model or a statistical model.

13. A device comprising:

at least one microphone for receiving an utterance in a first language from a user; and

a speech translation system in communication with the at least one microphone, wherein the speech translation system is configured for translating the utterance into a second language, and wherein the speech translation system comprises;

an automatic speech recognition module that recognizes the utterance in the first language;

a first machine translation module in communication with the first speech recognition module, wherein the first machine translation module translates the recognized speech in the first language into the second language;

an information extraction module that extracts one or more keywords from the utterance, the one or more keywords indicative of a topic and retrieving additional information related to the topic, based at least in part on the extracted keywords; and

a user interface in communication with the speech translation system for providing the translation of the utterance in the second language along with the additional information related to the topic.

14. The device of claim 13, wherein the information extraction module extracts keywords from system logs storing the utterance.

15. The device of claim 13, wherein the information extraction module retrieves the additional information related to the topic from internet third party source.

16. The device of claim 13, wherein the device comprises a portable device

17. A computer program product comprising a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by a processor, cause the processor to:

receiving from a user, an utterance in a first language;

translating, by a speech translation system, the utterance in the first language into a second language;

extracting, by the speech translation system, one or more keywords from the utterance, the keywords indicative of a topic;

retrieving additional information related to the topic, based at least in part on the extracted keywords; and

presenting to the user the additional information related to the topic.

18. The computer program product of claim 17, wherein the keywords are extracted based on their frequency and context.

19. The computer program product of claim 17, further comprising:

displaying simultaneously in text, on a user interface display of the speech translation system, at least (i) the received utterance in the first language, and (ii) the translation into the second language of the utterance.

20. The computer program product of claim 17, wherein translating the utterance in the first language into the second language comprises generating a translation in the second language via either a rule-based model or a statistical model.