System and method for generating phrases

• US 9,552,353 B2
• Filed: 01/21/2011
• Issued: 01/24/2017
• Est. Priority Date: 01/21/2011
• Status: Active Grant

• Current Assignee: Disney Enterprises Incorporated (The Walt Disney Company)
• Original Assignee: Disney Enterprises Incorporated (The Walt Disney Company)
• Inventors: Markman, Vita G., Veprinsky, Michael, Hughston, Roger H., Beechum, Andrew R., Trestman, Arkady G.
• Primary Examiner(s): WOZNIAK, JAMES S
• Application Number:
  US13/011,659
• Publication Number:
  US 20120191445A1
• Time in Patent Office: 2,195 Days
• Field of Search: 704/2, 704/4, 704/9, 704/10, 715/753, 715/758
• US Class Current: 1/1
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/45 Example-based machine translation; Alignment
• CPC Class Codes: G06F 40/55 Rule-based translation
• CPC Class Codes: G06F 40/56 Natural language generation

Abstract

Techniques are disclosed for generating phrases for selection by users communicating in an online virtual world environment. A phrase generation engine automatically constructs new phrases using pre-approved words from a dictionary of frequently used words and language-specific rules for phrase formation to ensure safety and supplement an existing database of commonly used, pre-approved phrases. Increasing the number of phrases that are available for selection by a user increases the user expressivity. Each word in the dictionary is annotated with semantic and grammatical information that constrains how the word is combined with other words to generate a new phrase. Each new phrase may also be tagged to enable translation into a different language so a phrase in a first language selected by a first user may be displayed in a second language to a second user.

Claims

1. A computer-implemented method for generating phrases, the method comprising:

receiving a dictionary storing a plurality of words of a first language and annotated with grammatical information and semantic information, wherein the annotated words are organized into groups based on meanings of the annotated words, wherein the annotated words in the dictionary are approved for use in a chat environment, and wherein the semantic information specifies a category for each word in the plurality of words based on a semantic meaning of that word;

generating, by operation of one or more computer processors, a plurality of chat phrases of the first language using combinations of the annotated words based on the grammatical information, semantic information, phrase formation rules, and the groups, wherein each phrase formation rule specifies how to generate one or more of the chat phrases by combining words from the dictionary based on the grammatical information and the semantic information;

storing the generated chat phrases in a memory;

creating a semantic tag for a first chat phrase of the plurality of chat phrases, wherein the semantic tag includes a plurality of words extracted from the first chat phrase;

translating the plurality of words within the semantic tag into a translated semantic tag of a second language;

translating the first chat phrase into a second chat phrase represented in the second language, by determining the second chat phrase matching the translated semantic tag; and

transmitting the second chat phrase to a client device of an online environment.

2. The method of claim 1, wherein the semantic tag includes a verb and a verb argument extracted from the first chat phrase.

3. The method of claim 2, wherein the semantic tag includes an object extracted from the first chat phrase.

4. The method of claim 2, further comprising assigning a numeric identifier to the semantic tag.

5. The method of claim 2, further comprising storing the semantic tag in the memory.

6. The method of claim 2, further comprising translating the verb and verb argument from the first language to the second language to produce the translated semantic tag.

7. The method of claim 6, further comprising retrieving the second chat phrase that is represented in the second language and corresponds to the translated semantic tag.

8. The method of claim 1, wherein the phrase formation rules include a first set of rules corresponding to the first language and a second set of phrase rules corresponding to the second language and the annotated words include a first set of annotated words that are represented in the first language and a second set of annotated words that are represented in the second language.

9. The method of claim 1, further comprising:

receiving a selection from a first user of the online environment of the first chat phrase of the plurality of chat phrases; and

sending the second chat phrase to at least a second user of the online environment.

10. A system comprising:

a processor; and

a memory, wherein the memory includes a phrase generation engine, which, when executed on the processor, performs an operation that generates phrases, the operation comprising;

receiving a dictionary storing a plurality of approved words of a first language that are annotated with grammatical information and semantic information, wherein the annotated words are organized into groups based on meanings of the annotated words, wherein the annotated words in the dictionary are approved for use in a chat environment, and wherein the semantic information specifies a category for each word in the plurality of words based on a semantic meaning of that word;

generating a plurality of chat phrases of the first language using combinations of the annotated words based on the grammatical information, semantic information, phrase formation rules, and the groups, wherein each phrase formation rule specifies how to generate one or more of the chat phrases by combining words from the dictionary based on the grammatical information and the semantic information;

storing the generated chat phrases in a storage device,

creating a semantic tag for a first chat phrase of the plurality of chat phrases, wherein the semantic tag includes a plurality of words extracted from the first chat phrase;

translating the plurality of words within the semantic tag into a translated semantic tag of a second language;

translating the first chat phrase into a second chat phrase represented in the second language, by determining the second chat phrase matching the translated semantic tag; and

transmitting the second chat phrase to a client device of an online environment.

11. A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause a computer system to generate phrases, by performing the steps of:

receiving a dictionary storing a plurality of approved annotated words of a first language that are annotated with grammatical information and semantic information, wherein the annotated words are organized into groups based on meanings of the annotated words, wherein the annotated words in the dictionary are approved for use in a chat environment, and wherein the semantic information specifies a category for each word in the plurality of words based on a semantic meaning of that word;

generating a plurality of chat phrases of the first language using combinations of the annotated words based on the grammatical information, semantic information, phrase formation rules, and the groups, wherein each phrase formation rule specifies how to generate one or more of the chat phrases by combining words from the dictionary based on the grammatical information and the semantic information; and

storing the generated chat phrases in a memory;

creating a semantic tag for a first chat phrase of the plurality of chat phrases, wherein the semantic tag includes a plurality of words extracted from the first chat phrase;

translating the plurality of words within the semantic tag into a translated semantic tag of a second language;

translating the first chat phrase into a second chat phrase represented in the second language, by determining the second chat phrase matching the translated semantic tag; and

transmitting the second chat phrase to a client device of an online environment.

12. A computer-implemented method for translating phrases, the method comprising:

receiving a first generated phrase that is represented in a first language, wherein the first phrase is a chat message generated using a phrase formation rule specifying a rule for combining words from a dictionary of approved words based on grammatical information and semantic information associated with the approved words in the dictionary, wherein the semantic information specifies a category for each word in the dictionary of approved words based on a semantic meaning of that word;

determining a semantic tag for the first generated phrase, wherein the semantic tag includes a plurality of words extracted from the first generated phrase, wherein the plurality of words include a verb and a verb argument;

translating the plurality of words within the semantic tag into a second language to produce a translated semantic tag;

retrieving a second phrase represented in a second language that corresponds to the translated semantic tag; and

transmitting the second phrase to a first user of an online environment.

13. The method of claim 12, wherein the first generated phrase is selected by a second user of the online environment.

14. The method of claim 13, further comprising receiving a first character of the first generated phrase that is entered by the second user to initiate phrase chat with the first user.

15. The method of claim 14, further comprising displaying a set of generated phrases including the first generated phrase, wherein the generated phrases in the set of generated phrase each have a first character that matches the first character that is entered by the second user.

16. The method of claim 12, wherein the second phrase is generated using combinations of words represented in the second language that are annotated with semantic and grammatical information and combined based on phrase formation rules that are specific to the second language.

17. The method of claim 12, wherein the semantic tag includes an object extracted from the first generated phrase the object is translated into a second language to produce the translated semantic tag.

18. The method of claim 12, wherein the retrieving of the second phrase comprises matching a numeric identifier associated with the first generated phrase with a corresponding numeric identifier associated with the second phrase.

19. The method of claim 12, further comprising storing the semantic tag in a memory.

20. A system comprising:

a processor; and

a memory, wherein the memory stores a phrase translation engine, which, when executed on the processor, performs an operation that translates phrases, the operation comprising;

receiving a first generated phrase that is represented in a first language, wherein the first phrase is a chat message generated using a phrase formation rule specifying a rule for combining words from a dictionary of approved words based on grammatical information and semantic information associated with the approved words in the dictionary, wherein the semantic information specifies a category for each word in the dictionary of approved words based on a semantic meaning of that word;

determining a semantic tag for the first generated phrase, wherein the semantic tag includes a plurality of words extracted from the first generated phrase, wherein the plurality of words include a verb and a verb argument;

translating the plurality of words within the semantic tag into a second language to produce a translated semantic tag;

retrieving a second phrase represented in a second language that corresponds to the translated semantic tag; and

transmitting the second phrase to a first user of an online environment.

21. A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause a computer system to translate phrases, by performing the steps of:

receiving a first generated phrase that is represented in a first language, wherein the first phrase is a chat message generated using a phrase formation rule specifying a rule for combining words from a dictionary of approved words based on grammatical information and semantic information associated with the approved words in the dictionary, wherein the semantic information specifies a category for each word in the dictionary of approved words based on a semantic meaning of that word;

determining a semantic tag for the first generated phrase, wherein the semantic tag includes a plurality of words extracted from the first generated phrase, wherein the plurality of words include a verb and a verb argument;

translating the plurality of words within the semantic tag into a second language to produce a translated semantic tag;

retrieving a second phrase represented in a second language that corresponds to the translated semantic tag; and

transmitting the second phrase to a first user of an online environment.