1. A structure comprising: a nitridated material, wherein the nitridated material has the characteristic of capturing CO2, wherein the nitridated material has a surface selected from: a nitridated silica material, a nitridated metal oxide material surface, or a nitridated non-metal oxide material, wherein the nitridated material is formed through cyclic chlorination and ammoniation of a material to densify NH2 groups on the material surface, wherein cyclic chlorination and ammoniation includes dehydroxilation of the material followed by chlorination with thionyl chloride and ammonia adsorption and subjecting the ammoniated trichlorosilylated material to another exposure to trichlorosilylation ammoniation to form a surface having a network of surface \u2014Si(NH)2\u2014(NH)\u2014Si\u2014(HN2)2 or 3.
2. The structure of claim 1, wherein the nitridated silica material has a plurality of silicon-amine groups.
3. The structure of claim 1, wherein the nitridated metal oxide material has a plurality of metal oxide-amine groups.
4. The structure of claim 1, wherein the nitridated non-metal oxide material has a plurality of non-metal oxide-amine groups.
5. The structure of claim 1, wherein the nitridated material has a structure selected from: a porous structure, a non-porous structure, an amorphous structure, and a crystalline structure.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
1. A computer-implemented method of generating a natural language spoken dialog system, the method comprising:
at each turn in a dialog, nominating a set of allowed dialog actions and a set of contextual features;
selecting an optimal action from the set of nominated allowed dialog actions using a machine learning algorithm; and
generating a response based on the selected optimal action at each turn in the dialog.
2. The method of claim 1, wherein the machine learning algorithm uses reinforcement learning.
3. The method of claim 1, wherein the machine learning algorithm is partially observable Markov decision process (POMDP) based.
4. The method of claim 1, wherein the set of nominated allowed dialog actions incorporates a set of business rules.
5. The method of claim 4, wherein prompt wordings in the generated natural language spoken dialog system are tailored to a current context while following the set of business rules.
6. The method of claim 1, wherein a compression label represents at least one of the nominated allowed dialog actions.
7. A system for generating a natural language spoken dialog system, the system comprising:
a processor;
a module configured to control the processor to nominate allowed dialog actions and a set of contextual features at each turn of a dialog;
a module configured to control the processor to select an optimal action from the set of nominated allowed dialog actions at each dialog turn based on machine learning algorithm; and
a module configured to control the processor to generate a response based on the selected optimal action at each turn in the dialog.
8. The system of claim 7, wherein the system uses reinforcement learning.
9. The system of claim 7, wherein the system is partially observable Markov decision process (POMDP) based.
10. The system of claim 7, wherein the set of manually nominated allowed dialog actions incorporates a set of business rules.
11. The system of claim 10, wherein prompt wordings in the generated natural language spoken dialog system are tailored to a current context while following the set of business rules.
12. The system of claim 7, wherein a compression label represents at least one of the manually nominated allowed dialog actions.
13. A tangible computer-readable storage medium storing a computer program having instructions for controlling a processor to generate a natural language spoken dialog system, the instructions comprising:
nominating allowed dialog actions and a set of contextual features at each turn of a dialog;
selecting an optimal action from the set of manually nominated allowed dialog actions at each turn of a dialog based on machine learning algorithm; and
generating a spoken dialog system based on a process of selecting optimal actions at each dialog turn.
14. The tangible computer-readable storage medium of claim 13, wherein the machine learning algorithm uses reinforcement learning.
15. The tangible computer-readable storage medium of claim 13, wherein the machine learning algorithm is partially observable Markov decision process (POMDP) based.
16. The tangible computer-readable storage medium of claim 13, wherein the set of manually nominated allowed dialog actions incorporates a set of business rules.
17. The tangible computer-readable storage medium of claim 16, wherein prompt wordings in the generated natural language spoken dialog system are tailored to a current context while following the set of business rules.