Refining training sets and parsers for large and dynamic text environments

1. A system for training a parser based on a semantically matched knowledge structure, comprising:

a first device for refining at least a portion of an ontology and a parser;

a network for communicating data; and

a second device connected to the first device through the network, wherein the second device performs steps comprising:

constraint-matching a query semantic sequence received through the input component with a candidate semantic sequence stored on the memory component based on maximizing a plurality of constraints,

wherein at least one of the plurality of the constraints is a similarity score between a subsequence of the query semantic sequence and another subsequence of the candidate semantic sequence, and

wherein the constraint matching generates a matched sequence and an associated matching score;

finding the candidate semantic sequence for constraint-matching with the query semantic sequence, wherein the finding is based at least in part on a semantic comprised in the query semantic sequence;

adding a resulting semantic sequence chosen between the matched sequence and another matched sequence based at least in part on a comparison of the associated matching score and another associated matching score of the other matched sequence to a training set for further training the parser; and

providing a change in a data structure representing a change in the parser based the candidate semantic sequence for constraint-matching.

2. The system of claim 1 , wherein the parser is used for at least one of parsing another candidate semantic sequence, parsing text to determine a ranking of an action, or summarization.

3. The system of claim 1 , wherein the parser is a semantic-syntactic parser use for frame-slot matching.

4. The system of claim 1 , wherein the parser is used to provide a trust measure for a content provided based on parsing a search query, and wherein the trust measure comprises at least one of a quality of service a reputation, or an informativeness measure.

5. The system of claim 1 , wherein the ontology comprises a neural network.

6. The system of claim 5 , wherein the refining comprises the neural network training of words or items in the ontology to create affinities between the words or items for measuring similarities in a vector space.

7. The system of claim 1 , wherein the matching score is based on a function of a plurality of similarity scores for matched subsequences.

8. The system of claim 1 , wherein the matched sequence comprises a matched subsequence that is matched against a query subsequence comprised in the query semantic, and wherein the matched subsequence is matched against a candidate subsequence comprised in the candidate semantic sequence.

9. The system of claim 1 , wherein the steps further comprise:

generating the query semantic sequence based at least in part on a sequence of semantic heads of sub-trees from a level of a natural language parse tree of a query sentence.

10. The system of claim 1 , wherein the steps further comprise:

generating the query semantic sequence based at least in part a portion of leaves of a natural language parse tree of a sentence.

11. A device for retrieving a semantically matched knowledge structure, comprising:

an input component for receiving an input;

a memory component for storing a dense semantic vector indication of concepts;

a processor connected to the input component and the memory component, wherein the processor performs steps comprising:

constraint-matching a query semantic sequence received through the input component with a candidate semantic sequence stored on the memory component based on maximizing a plurality of constraints; and

providing a candidate semantic sequence for constraint-matching with the query semantic sequence, wherein the providing is based at least in part on a semantic comprised in the query semantic sequence and at least in part on a comparison of the associated matching score and another associated matching score of the other matched sequence.

12. The device of claim 11 , wherein the query semantic sequence is matched to the candidate semantic sequence that comprises an ad based sentence, and wherein a website associated with the ad based sentence is provided.

13. The device of claim 11 , wherein the constraint-matching of the query semantic sequence comprises semantic parsing constraint-matching a query semantic sequence based on a real world variable, wherein the real world variable comprises at least one of a level of employment, a commodity available for consumption, an equity, a debt, or a popularity of a good.

14. The device of claim 11 , wherein the steps further comprise:

providing the query semantic sequence based at least in part on a sequence of semantic nodes in a natural language parse tree of a query sentence; and

determining an answer slot-hint for the query sentence; and retrieving an answer semantic from the matched sequence based at least in part on a comparison of a slot-hint of the answer semantic and the answer slot-hint.

15. The device of claim 11 , wherein the steps further comprise:

selecting the candidate sequence from a search result list provided by a query-expansion search for, in part, a search term based on the semantic.

16. The device of claim 11 , wherein constraint-matching the query semantic sequence with the candidate semantic sequence comprises at least one of a common subsequence match, a Rabin-Karp pattern match, a Knuth-Morris-Pratt pattern match, Boyer-Moore pattern match, or a Diff pattern match.

17. A method for retrieving a semantically matched knowledge structure, comprising:

receiving a text pair;

constraint-matching a first part of the text pair with a second part of the text pair based on a plurality of constraints, wherein at least one of the plurality of the constraints is a similarity score between the first part of the text pair and the second part of the text pair;

providing a slot-frame of a matched sequence based on the constraint matching of the first part of the text pair with the second part of the text pair; and

generalizing a parser based on the slot-frame.

18. The method of claim 17 , wherein the parser is generalized based on the slot-frame to perform shallow semantic parsing.

19. The method of claim 17 , wherein the parser is used to provide at least one chat response based on extracting a semantic information from an input to the parser.

20. The method of claim 17 , wherein the parser is used to parse an input based on the slot-frame and at least one of a location, a time, or a social network.