Systems and methods for determining translation accuracy in multi-user multi-lingual communications
US-9448996-B2 · Sep 20, 2016 · US
US9600473B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-9600473-B2 |
| Application number | US-201313763565-A |
| Country | US |
| Kind code | B2 |
| Filing date | Feb 8, 2013 |
| Priority date | Feb 8, 2013 |
| Publication date | Mar 21, 2017 |
| Grant date | Mar 21, 2017 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Various embodiments described herein facilitate multi-lingual communications. The systems and methods of some embodiments may enable multi-lingual communications through different modes of communications including, for example, Internet-based chat, e-mail, text-based mobile phone communications, postings to online forums, postings to online social media services, and the like. Certain embodiments may implement communications systems and methods that translate text between two or more languages (e.g., spoken), while handling/accommodating for one or more of the following in the text: specialized/domain-related jargon, abbreviations, acronyms, proper nouns, common nouns, diminutives, colloquial words or phrases, and profane words or phrases.
Opening claim text (preview).
What is claimed is: 1. A computer-implemented method comprising: obtaining, using one or more computer processors, an initial message in a first language authored by a first person; querying, using the one or more computer processors, a data store for a first corresponding message in a second language, the first corresponding message being a translation of the initial message; determining, using the one or more computer processors, that the data store does not include the first corresponding message and, based thereon: providing, using the one or more computer processors, the initial message to an initial transformation module in a sequence of transformation modules, each transformation module other than the initial transformation module being configured to accept, as input, an output of an immediately preceding transformation module in the sequence and provide, as output, a respective transformed message, and wherein a particular transformation module in the sequence is configured to flag at least a portion of the particular transformation module's output as not to be transformed by subsequent transformation modules in the sequence; selecting, using the one or more computer processors, output of the final transformation module in the sequence as a transformed message in the first language; and querying, using the one or more computer processors, the data store for a second corresponding message in the second language, the second corresponding message being a translation of the transformed message in the first language. 2. The method of claim 1 , further comprising providing the initial message or the transformed message to a machine translation system to obtain a third corresponding message in the second language. 3. The method of claim 2 , wherein the transformed message is translated to the third corresponding message in the second language if the data store does not include the second corresponding message. 4. The method of claim 2 , wherein the initial message is translated to the third corresponding message in the second language if the transformation modules do not transform at least a portion of the initial message. 5. The method of claim 1 , wherein one of the transformation modules performs the following: identifying a chatspeak word or phrase in the initial message; and replacing the chatspeak word or phrase with a non-chatspeak word or phrase. 6. The method of claim 1 , wherein one of the transformation modules performs a spelling check on the initial message. 7. The method of claim 1 , wherein one of the transformation modules performs the following: identifying an abbreviation in the initial message; and replacing the abbreviation with a word or a phrase corresponding to the abbreviation. 8. The method of claim 1 , wherein one of the transformation modules performs the following: identifying an acronym in the initial message; and replacing the acronym with a word or a phrase corresponding to the acronym. 9. The method of claim 1 , wherein one of the transformation modules performs the following: identifying a colloquial word or phrase in the initial message; and replacing the colloquial word or phrase with a word or a phrase representing the colloquial word or phrase. 10. The method of claim 1 , wherein one of the transformation modules performs the following: identifying a profane word or phrase in the initial message; and replacing the profane word or phrase with a non-profane word or phrase or removing the profane word or phrase. 11. The method of claim 1 , wherein the initial message comprises text. 12. The method of claim 1 , wherein the initial message comprises an emoticon. 13. The method of claim 1 , wherein the initial message is part of a larger message. 14. The method of claim 1 , wherein the portion flagged comprises a proper noun, a common noun, a diminutive, an abbreviation, or an acronym. 15. The method of claim 1 , wherein the data store comprises at least one of an untransformed translation and a transformed translation. 16. A system comprising: one or more computer processors programmed to perform operations comprising: identifying, using the one or more computer processors, the first language and the second language; obtaining, using the one or more computer processors, an initial message in the first language from the first chat client system; querying, using the one or more computer processors, the data store for a first corresponding message in the second language, the first corresponding message being a translation of the initial message; determining, using the one or more computer processors, that the data store does not include the first corresponding message and, based thereon: providing, using the one or more computer processors, the initial message to an initial transformation module in a sequence of transformation modules, each transformation module other than the initial transformation module being configured to accept, as input, an output of an immediately preceding transformation module in the sequence and provide, as output, a respective transformed message, and wherein a particular transformation module in the sequence is configured to flag at least a portion of the particular transformation module's output as not to be transformed by subsequent transformation modules in the sequence; selecting, using the one or more computer processors, output of the final transformation module in the sequence as a transformed message in the first language; and querying, using the one or more computer processors, the data store for a second corresponding message in the second language, the second corresponding message being a translation of the transformed message in the first language. 17. The system of claim 16 , wherein the operations further comprise providing the initial message or the transformed message to a machine translation system to obtain a third corresponding message in the second language. 18. The system of claim 17 , wherein the transformed message is translated to the third corresponding message in the second language if the data store does not include the second corresponding message. 19. The system of claim 17 , wherein the initial message is translated to the third corresponding message in the second language if the transformation modules do not transform at least a portion of the initial message. 20. The system of claim 16 , wherein one of the transformation modules is configured to perform operations comprising: identifying a chatspeak word or phrase in the initial message; and replacing the chatspeak word or phrase with a non-chatspeak word or phrase. 21. The system of claim 16 , wherein one of the transformation modules is configured to perform a spelling check on the initial message. 22. The system of claim 16 , wherein one of the transformation modules is configured to perform operations comprising: identifying an abbreviation in the initial message; and replacing the abbreviation with a word or a phrase corresponding to the abbreviation. 23. The system of claim 16 , wherein one of the transformation modules is configured to perform operations comprising: identifying an acronym in the initial message; and replacing the acronym with a word or a phrase corresponding to the acronym. 24. The system of claim 16 , wherein one of the transformation modules is configured to perform operations comprising: identifying a colloquial word or phr
Orthographic correction, e.g. spell checking or vowelisation · CPC title
Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation · CPC title
Machine-assisted translation, e.g. using translation memory · CPC title
Editing, e.g. inserting or deleting · CPC title
Language identification · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.