SYSTEM AND METHOD FOR CONTEXT TRANSLATION OF NATURAL LANGUAGE

• US 20130166276A1
• Filed: 02/21/2013
• Published: 06/27/2013
• Est. Priority Date: 10/26/2005
• Status: Active Grant

• Current Assignee: Cortica Ltd.
• Original Assignee: Cortica Ltd.
• Inventors: ZEEVI, Yehoshua Y., RAICHELGAUZ, Igal, ODINAEV, Karina
• Granted Patent: US 9,087,049 B2
• Time in Patent Office: Days
• US Class Current: 704/2
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• 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: H04N 21/234336 by media transcoding, e.g. video is transformed into a slideshow of still pictures or audio is converted into text
• CPC Class Codes: H04N 21/25891 being end-user preferences retrieval of video data in a video database based on user preferences G06F16/739; arrangements for recognizing users' preferences H04H60/46; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/2668 Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles information retrieval from the Internet by querying with filtering and personalisation G06F16/9535; arrangements for replacing or switching information during the broadcast H04H20/10; push services over packet-switching network H04L12/1859; adaptation of message content in packet-switching networks H04L51/063
• CPC Class Codes: H04N 21/466 Learning process for intelligent management, e.g. learning user preferences for recommending movies services using the results of monitoring in broadcast systems H04H60/61
• CPC Class Codes: H04N 21/8106 involving special audio data, e.g. different tracks for different languages
• CPC Class Codes: H04N 21/8358 involving watermark protecting executable software by watermarking G06F21/16; image watermarking in general G06T1/0021; watermarks inserted in still images for transmission purposes H04N1/32144; inserting watermarks during video coding H04N19/467
• CPC Class Codes: H04N 7/17318 Direct or substantially direct transmission and handling of requests

Abstract

A method for translating natural language text. The method comprises receiving at least one multimedia element including a first natural language text; generating metadata representing the first natural language text; generating at least one signature for the at least one multimedia element; determining the context of the at least one multimedia element respective of the signature; and searching for a multimedia content element (MMCE) corresponding to the received at least one multimedia element that includes a second natural language text, wherein the search is performed using the at least one signature, the context and metadata generated for the at least input text in a first natural language respective of the context, wherein the second natural language text is a translated text of the first natural language text.

Claims

1. A method for translating natural language text, comprising:

receiving at least one multimedia element including a first natural language text;

generating metadata representing the first natural language text;

generating at least one signature for the at least one multimedia element;

determining the context of the at least one multimedia element respective of the signature; and

searching for a multimedia content element (MMCE) corresponding to the received at least one multimedia element that includes a second natural language text, wherein the search is performed using the at least one signature, the context and metadata generated for the at least input text in a first natural language respective of the context, wherein the second natural language text is a translated text of the first natural language text.

2. The method of claim 1, further comprising:

identifying the first natural language text in the received at least one multimedia element.

3. The method of claim 1, further comprising:

generating at least one signature for the first natural language text;

determining the context of the first natural language text; and

searching for a corresponding MMCE also using the at least one signature and context generated for the first natural language text.

4. The method of claim 1, wherein the metadata includes at least one of:

identifiers of the first language text, amount of words in the first language text, letters in the first language text, phonemic information, and appearance of the text.

5. The method of claim 1, wherein searching for the corresponding MMCE further comprises:

searching a data warehouse for MMCEs that match the context and the at least one signature;

comparing metadata associated with each MMCE retrieved through the search to the metadata generated for the first natural language search; and

returning the MMCE that matches the metadata generated for the first natural language search.

6. The method of claim 1, wherein the first natural language text includes any one of speech and vocal in the first natural language.

7. The method of claim 1, wherein the at least one signature is robust to noise and distortion.

8. The method of claim 1, wherein the multimedia content is at least one of:

an image, graphics, a video stream, a video clip, an audio stream, an audio clip, a video frame, a photograph, images of signals, combinations thereof, and portions thereof.

9. A non-transitory computer readable medium having stored thereon instructions for causing one or more processing units to execute the method according to claim 1.

10. A system for translating natural language text, comprising:

an interface to a network for receiving at least one multimedia element including a first natural language text; and

a translation engine for generating metadata representing the first natural language text, wherein the translation engine is further configured to determine the context of the at least one multimedia element respective of the signature and search for a MMCE corresponding to the received at least one multimedia element that includes a second natural language text, wherein the search is performed using at least one signature, the context, and metadata generated for the at least input text in a first natural language respective of the context, wherein the second natural language text is a translated text of the first natural language text.

11. The system of claim 10, further comprising:

a signature generator system (SGS) for generating the at least one signature for the at least one received multimedia element and at least one signature for the at least one first natural language input text, wherein each of the at least one signature is robust to noise and distortion.

12. The system of claim 11, wherein the signature generator system further comprises:

a plurality of computational cores configured to receive the at least one multimedia element, each computational core of the plurality of computational cores having properties that are at least partly statistically independent from other of the plurality of computational cores, the properties are set independently of each other core.

13. The system of claim 10, further comprises:

a data warehouse for maintaining a plurality of MMCEs and their respective metadata.

14. The system of claim 10, wherein the translation engine is further configured to:

identify the first natural language text in the received at least one multimedia element.

15. The system of claim 10, wherein the translation engine is further configured to:

generate at least one signature for the first natural language text;

determine the context of the first natural language text; and

search for a corresponding MMCE also using the at least one signature and context generated for first natural language text.

16. The system of claim 10, wherein the metadata includes at least one of:

identifiers of the first language text, amount of words in the first language text, letters in the first language text, phonemic information, and appearance of the text.

17. The system of claim 10, wherein the translation engine is further configured to:

search a data warehouse for MMCEs that match the context and the at least one signature;

compare metadata associated with each MMCE retrieved through the search to the metadata generated for the first natural language search; and

return the MMCE that matches the metadata generated for the first natural language search.

18. The system claim 10, wherein the first natural language text includes any one of speech and vocal in the first natural language.

19. The system of claim 10, wherein the multimedia content is at least one of:

an image, graphics, a video stream, a video clip, an audio stream, an audio clip, a video frame, a photograph, images of signals, combinations thereof, and portions thereof.