Authoring speech grammars

• US 20060277031A1
• Filed: 06/02/2005
• Published: 12/07/2006
• Est. Priority Date: 06/02/2005
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Ramsey, William D.
• Granted Patent: US 7,617,093 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06Q 30/04 Billing or invoicing
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules

Abstract

A method and apparatus are provided for automatically forming a grammar. Example text strings are received and N-grams are formed based on the text strings. A rule in the grammar is then generated automatically based in part on the n-grams.

Claims

1. A method of automatically constructing a grammar, the method comprising:

receiving example input text strings;

forming n-grams based on the input text strings; and

automatically generating a rule in the grammar based in part on the n-grams.

2. The method of claim 1 wherein forming n-grams comprises:

receiving at least one class definition comprising a semantic class and at least one text sub-string associated with the semantic class;

replacing a text sub-string in an example input text string with a tag for a semantic class associated with the text sub-string to form a modified input text string; and

forming n-grams from the modified input text string.

3. The method of claim 1 wherein forming n-grams comprises forming different orders of n-grams.

4. The method of claim 2 wherein generating a rule further comprises generating a separate rule for each specific n-gram found in the modified input text strings.

5. The method of claim 4 wherein generating a rule for a specific n-gram comprises including an entry in the rule to allow the specific n-gram to appear in a position where it did not appear in the input text strings.

6. The method of claim 5 wherein generating a rule for a specific n-gram further comprises placing an entry in the rule that includes a reference to a rule for the tag or word in the last position of the n-gram followed by a reference to a rule for at least one n+1-gram.

7. The method of claim 6 wherein the reference to a rule for the tag comprises a reference to a rule that lists all words associated with the semantic class of the tag.

8. The method of claim 2 wherein replacing a text sub-string with a tag comprises replacing as many words as possible in the input text string with tags.

9. The method of claim 2 wherein receiving a class definition comprises receiving a reference to a class defined in an existing grammar.

10. A computer-readable medium having computer-executable components that form a programming interface responsive to method calls, the programming interface comprising:

components for receiving a method call to transmit a text string associated with a semantic class to the programming interface;

components for receiving a method call to transmit at least one sentence in which the text string appears to the programming interface; and

components for receiving a method call to generate a grammar in a particular grammar format based on the at least one sentence and the semantic class.

11. The computer-readable medium of claim 10 wherein the method call to transmit a text string comprises:

a text string parameter that identifies the text string;

a semantic class parameter that identifies the semantic class; and

a weight parameter that indicates the relative weight to be assigned to the text string in the semantic class.

12. The computer-readable medium of claim 10 wherein the method call to transmit at least one sentence comprises:

a sentence parameter that identifies the sentence; and

a weight parameter that indicates a weight for the sentence in the grammar.

13. The computer-readable medium of claim 10 wherein the method call to generate a grammar comprises:

a grammar output file parameter that designates the name to be given to the file containing the grammar; and

a grammar format parameter that designates the format for the grammar.

14. The computer-readable medium of claim 10 further comprising components to receive a method call to define a semantic class.

15. The computer-readable medium of claim 14 wherein the method call to define the semantic class comprises:

a main semantic class parameter that provides a main semantic class for the semantic class;

an indicator semantic class parameter that defines an indicator semantic class for the semantic class; and

an active node parameter that indicates whether the combination of the indicator semantic class and the main semantic class should be used as the default for the main semantic class.

16. The computer-readable medium of claim 15 wherein the main semantic class parameter comprises a reference to a semantic class in an external grammar.

17. A method of forming a grammar, the method comprising:

displaying a user interface that provides a text area for a user to enter text strings representing expected word sequences and an area for associating text sub-strings with a semantic class;

forming modified text strings by replacing at least one text sub-string in the text strings with a tag for a semantic class associated with the text sub-string; and

using the modified text strings to form the grammar.

18. The method of claim 17 further comprising identifying n-grams of a plurality of orders in the modified text strings.

19. The method of claim 18 further comprising forming a separate rule in the grammar for each identified n-gram.

20. The method of claim 17 wherein using the modified text strings to form the grammar comprises providing rules in the grammar for word sequences that were not present in the text strings.