Systems and methods for generating markup-language based expressions from multi-modal and unimodal inputs
View Patent ↗When using finite-state devices to perform various functions, it is beneficial to use finite state devices representing regular grammars with terminals having markup-language-based semantics. By using markup-language-based symbols in the finite state devices, it is possible to generate valid markup-language expressions by concatenating the symbols representing the result of the performed function. The markup-language expression can be used by other applications and/or devices. Finite-state devices are used to convert strings of words and gestures into valid markup-language, for example, XML, expressions that can be used, for example, to provide an application program interface to underlying system applications.
1. A method comprising:
generating, via a processor, from an input lattice representing a first modality of an input, a first markup-language expression;
generating, via a finite-state transducer, a concatenated mapping, wherein the finite-state transducer:
uses the input lattice and a first finite-state machine having associated markup-language semantics to relate the first markup-language expression to a second markup-language expression representing a second modality based on a level of coincidence between the first modality and the second modality, to yield a mapping; and
concatenates input symbols of the mapping associated with the markup-language semantics, to yield the concatenated mapping;
generating, using the input and a second finite-state machine representing the concatenated mapping, a third markup-language expression; and
outputting the third markup-language expression.
2. The method of claim 1 , further comprising a finite-state machine representing a regular grammar comprising markup language tags in a terminal of the regular grammar.
3. The method device of claim 1 , further comprising a finite-state device representing a regular grammar comprising markup-language tags in a result-part of a terminal of the regular grammar.
4. The method of claim 2 , further comprising:
generating a result-finite-state machine representing a multimodal integration by relating a set of input symbols to a set of output symbols, wherein the input lattice is associated with the multimodal integration.
5. The method of claim 2 , further comprising converting a sequence of words into a sequence of markup-language symbols using the third markup-language expression.
6. The method of claim 1 , wherein the input comprises a command received via at least one of a speech input subsystem, a pen input subsystem, a computer vision input subsystem, a haptic input subsystem, a gaze input subsystem, and a body motion input subsystem.
7. The method of claim 1 , further comprising using extensible-markup-language-based symbols in the first finite state machine.
8. The method of claim 1 , further comprising using the third markup-language expression to perform another function.
9. A system comprising:
a processor; and
a computer-readable medium storing instructions for controlling the processor to perform a method comprising:
generating, from an input lattice representing a first modality of an input, a first markup-language expression;
generating, via a finite-state transducer, a concatenated mapping, wherein the finite-state transducer:
uses the input lattice and a first finite-state machine having associated markup-language semantics to relate the first markup-language expression to a second markup-language expression representing a second modality based on a level of coincidence between the first modality and the second modality, to yield a mapping; and
concatenates input symbols of the mapping associated with the markup-language semantics, to yield the concatenated mapping;
generating, using the input and a second finite-state machine representing the concatenated mapping, a third markup-language expression; and
outputting the third markup-language expression.
10. The system of claim 9 , wherein the finite-state transducer further uses a regular grammar comprising markup-language tags.
11. The system of claim 10 , wherein the finite-state transducer further uses a regular grammar comprising markup-language tags in a result-part of a terminal of the regular grammar.
12. The system according to claim 10 , wherein the computer-readable storage medium stores further instructions which result in the method further comprising:
generating a result-finite-state machine relating a set of input symbols to a set of output symbols representing a multimodal integration, wherein the input lattice is used for the multimodal integration.
13. The system of claim 9 , wherein the input comprises a command received via at least one of a speech input subsystem, a pen input subsystem, a computer vision input subsystem, a haptic input subsystem, a gaze input subsystem, and a body motion input subsystem.
14. The system of claim 9 , wherein the finite-state transducer further uses extensible-markup-language-based symbols.
15. The system of claim 9 , wherein the computer-readable storage medium stores further instructions which result in the method further comprising using the third markup-language expression to perform another function.
16. A computer-readable storage medium storing instructions which, when executed by a computing device, cause the computing device to perform a method comprising:
generating, from an input lattice representing a first modality of an input, a first markup-language expression;
generating, via a finite-state transducer, a concatenated mapping, wherein the finite state transducer:
uses the input lattice and a first finite-state machine having associated markup-language semantics to relate the first markup-language expression to a second markup-language expression representing a second modality based on a level of coincidence between the first modality and the second modality, to yield a mapping; and
concatenates input symbols of the mapping associated with the markup-language semantics, to yield the concatenated mapping;
generating, using a second finite-state machine representing the concatenated mapping and the input, a third markup-language expression; and
outputting the third markup-language expression.
17. The computer-readable storage medium of claim 16 , wherein generating the concatenated mapping further comprises using a finite-state device representing a regular grammar comprising markup language tags in a terminal of the regular grammar.
18. The computer-readable storage medium of claim 17 , wherein generating the mapping further comprises using the finite-state device in a result-part of the terminal of the regular grammar.
19. The computer-readable storage medium of claim 17 , the computer-readable storage medium storing additional instructions which result in the method further comprising generating a result-finite-state machine relating a set of input symbols to a set of output symbols representing a multimodal integration, wherein the multimodal integration uses the input lattice.
20. The computer-readable storage medium of claim 16 , wherein the input comprises a command received via at least one of a speech input subsystem, a pen input subsystem, a computer vision input subsystem, a haptic input subsystem, a gaze input subsystem, and a body motion input subsystem.
21. The computer-readable storage medium of claim 16 , wherein using the first finite-state device and the second finite-state device to perform a function using the input lattice comprises using extensible-markup-language-based symbols in the finite state device having symbols based on markup-language semantics.
22. The computer-readable storage medium of claim 16 , the computer-readable storage medium storing additional instructions which result in the method further comprising using the generated markup-language expression to another function.