Methods and systems for generation of a translatable sentence syntax in a social networking system

• US 10,430,520 B2
• Filed: 02/13/2017
• Issued: 10/01/2019
• Est. Priority Date: 05/06/2013
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Bao, Ling, van Heuven, Hugo Johan, Miao, Jiangbo, Tan, Li, Mercurio, David, Machedon, Maximilian
• Primary Examiner(s): Sarpong, Akwasi M
• Application Number:
  US15/431,330
• Publication Number:
  US 20170169016A1
• Time in Patent Office: 960 Days
• Field of Search: 704 1, 704 4, 704 3
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06F 30/00 Computer-aided design [CAD]
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/45 Example-based machine translation; Alignment
• CPC Class Codes: G06F 40/47 Machine-assisted translation, e.g. using translation memory
• CPC Class Codes: G06F 40/56 Natural language generation
• 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

Sentence internationalization methods and systems are disclosed. The method may include: providing a developer interface to define an internationalized sentence syntax for an application on a social networking system, the internationalized sentence syntax for translating a natural language expression of a social graph edge of the social networking system; providing a sentence option on the developer interface to define grammar of the internationalized sentence syntax; generating a token structure including a language token to assist translation of the internationalized sentence syntax into a preferred language indicated by the language token, the token structure customizable via the developer interface to configure translation options; associating a social graph attribute with a first token of the token structure; and storing the sentence option and the token structure with the internationalized sentence syntax to facilitate run-time translation of the internationalized sentence syntax into the natural language expression in the preferred language.

Claims

1. A method, comprising:

accessing a part of a social graph, wherein the part of the social graph comprises an actor node and a target node corresponding to actor and target entities respectively within a social networking system and an edge connecting the actor and target nodes corresponding to an action or relationship between the actor and target entities; and

generating an internationalized sentence syntax representing an expression of the action or relationship comprising;

an actor element corresponding to the actor node;

a target element corresponding to the target node;

an edge element corresponding to the edge connecting the actor and target nodes; and

a token structure that includes one or more tokens identifying one or more social graph attributes, the one or more social graph attributes related to the actor element, the target element, the edge element or to an intended viewer of the expression of the action or relationship;

wherein one of the one or more tokens is associated with the actor element of the internationalized sentence syntax and identifies a gender as the corresponding social graph attribute;

generating an expression of the action or relationship into an output language from the internationalized sentence syntax by;

identifying one or more edges or nodes of the social graph that correspond to the actor element, the target element and the edge element;

matching each of the one or more tokens in the token structure of the internationalized sentence syntax with an attribute of the identified edges or nodes; and

generating the expression of the action or relationship in the output language based on the identified nodes, edges and attributes;

wherein identifying one or more attributes comprises identifying a gender value associated with a node of the social graph; and

wherein the generating the expression of the action or relationship in the output language is based on the identified gender value.

2. The method of claim 1, wherein one of the one or more tokens, is associated with the target element of the internationalized sentence syntax and identifies whether the target entity is possessive or nominative.

3. The method of claim 1, wherein one of the one or more or more tokens is associated with the target element or the actor element of the internationalized sentence syntax and specifies a numeric attribute indicating whether the target entity or actor entity is singular or plural.

4. The method of claim 1, wherein one of the one or more tokens corresponds to a potential viewer of the generated expression of the action or relationship and specifies a gender attribute or a seniority attribute of the potential viewer.

5. The method of claim 1, wherein the generation of the expression of the action or relationship further comprises:

generating a raw sentence from the internationalized sentence syntax;

exporting the raw sentence to a third party for translation to one or more target languages; and

importing the translations from the third party.

6. The method of claim 5, wherein the translations imported from the third party include translations to multiple variations of the internationalized sentence syntax.

7. The method of claim 1, wherein identifying one or more edges or nodes of the social graph is based on a viewer of the generated expression of the action or relationship.

8. The method of claim 1, wherein the social graph attribute identified by each of the one or more tokens is based on whether the token corresponds to the actor element, the target element, or the edge element.

9. A non-transitory computer-readable storage medium storing instructions that, when executed by a computing system, cause the computing system to perform operations comprising:

generating an internationalized sentence syntax comprising;

an actor element;

a target element;

an edge element representing an action or relationship between the actor element and the target element; and

a token structure including one or more tokens identifying one or more social graph attributes, the one or more social graph attributes related to the actor element, the target element, the edge element, or to an intended viewer of the expression of the action relationship;

wherein one of the one or more tokens is associated with the actor element of the internationalized sentence syntax and identifies a gender as the corresponding social graph attribute;

generating an expression of the action or relationship into an output language from the internationalized sentence syntax by;

identifying one or more edges or nodes of the social graph that correspond to the elements of internationalized sentence syntax;

matching each of the one or more tokens in the token structure of the internationalized sentence syntax with an attribute of the identified edges or nodes; and

generating the expression of the action relationship in the output language based on the identified nodes, edges and attributes;

wherein identifying one or more attributes comprises identifying a gender value associated with a node of the social graph; and

wherein the generating the expression of the action or relationship in the output language is based on the identified gender value will.

10. The computer-readable storage medium of claim 9,

wherein one of the one or more tokens is associated with the target element of the internationalized sentence syntax and identifies that the target element is possessive;

wherein the identifying one or more attributes comprises selecting a possessive value associated with a node of the social graph; and

wherein generating the expression of the action or relationship in the output language is based on the identified possessive value.

11. The computer-readable storage medium of claim 9, wherein one of the one or more or more tokens is associated with the target element or the actor element of the internationalized sentence syntax and specifies a numeric attribute indicating being whether the target element or actor element is singular or plural.

12. The computer-readable storage medium of claim 9, wherein identifying one or more edges or nodes of the social graph is based on a viewer of the generated expression of the action or relationship.

13. The computer-readable storage medium of claim 9, wherein the social graph attribute identified by each of the one or more tokens is based on whether the token corresponds to the actor element, the target element, or the edge element.

14. A system comprising:

one or more processors; and

a memory storing instructions that, when executed by a computing system, cause the computing system to perform operations that generate an internationalized sentence syntax comprising;

an actor element;

a target element;

an edge element representing an action or relationship between the actor element and the target element; and

a token structure including one or more tokens identifying one or more social graph attributes, the one or more social graph attributes related to the actor element, the target element, the edge element or to an intended viewer of the expression of the action relationship;

wherein one of the one or more tokens is associated with the actor element of the internationalized sentence syntax and identifies a gender as the corresponding social graph attribute;

wherein the internationalized sentence syntax is used to generate an expression of the action or relationship into an output language by;

identifying one or more edges or nodes of the social graph that correspond to the internationalized sentence syntax;

matching each of the one or more tokens in the token structure of the internationalized sentence syntax with an attribute of the identified edges or nodes; and

generating the expression of the action relationship in the output language based on the identified nodes, edges and attributes

wherein identifying one or more attributes comprises identifying a gender value associated with a node of the social graph; and

wherein the generating expression of the action or relationship in the output language is based on the identified gender value.

15. The system of claim 14, wherein the social graph attribute identified by each particular token of the one or more tokens is based on whether the token corresponds to the actor element, the target element, edge element.