Dynamic natural language understanding
First Claim
Patent Images
1. A method for use in a method for understanding a natural language text, comprising performing the following selectively in a statistical manner:
- attempting to extract at least one value belonging to a semantic category from a natural language text or a form thereof; and
if a result of said attempting complies with a predetermined criterion, attempting to extract, based on said result, at least one value belonging to another semantic category of a different hierarchical level than said semantic category, else performing at least one action from a group of actions including;
asking a submitter of said text a question whose content depends on said result and giving up on understanding said natural language text;
wherein said attempting to extract at least one value belonging to said another semantic category includes;
developing at least one syntactic token based on at least one extracted value belonging to said semantic category;
embedding said at least one syntactic token in at least one restatement of said text; and
attempting to extract from said at least one restatement with embedded tokens or a form thereof at least one value belonging to said another semantic category.
2 Assignments
0 Petitions
Accused Products
Abstract
Methods and systems for dynamic natural language understanding. A hierarchical structure of semantic categories is exploited to assist in the natural language understanding. Optionally, the natural language to be understood includes a request.
417 Citations
13 Claims
-
1. A method for use in a method for understanding a natural language text, comprising performing the following selectively in a statistical manner:
-
attempting to extract at least one value belonging to a semantic category from a natural language text or a form thereof; and if a result of said attempting complies with a predetermined criterion, attempting to extract, based on said result, at least one value belonging to another semantic category of a different hierarchical level than said semantic category, else performing at least one action from a group of actions including;
asking a submitter of said text a question whose content depends on said result and giving up on understanding said natural language text;wherein said attempting to extract at least one value belonging to said another semantic category includes; developing at least one syntactic token based on at least one extracted value belonging to said semantic category; embedding said at least one syntactic token in at least one restatement of said text; and attempting to extract from said at least one restatement with embedded tokens or a form thereof at least one value belonging to said another semantic category. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A method for use in a method for understanding a natural language text, comprising performing the following selectively in a statistical manner:
-
attempting to extract at least one value belonging to a semantic category from a natural language text or a form thereof; if a result of said attempting complies with a predetermined criterion, attempting to extract, based on said result, at least one value belonging to another semantic category of a different hierarchical level than said semantic category, else performing at least one action from a group of actions including;
asking a submitter of said text a question whose content depends on said result and giving up on understanding said natural language text; andif said question is asked, attempting to extract at least one value belonging to a previously extracted semantic category from an answer to said question; wherein said attempting to extract at least one value from said answer includes; selecting at least one pseudo classifier from among more than said at least one pseudo classifier for said previously extracted semantic category, wherein said selecting is based on at least one extracted value belonging to a different previously extracted semantic category; and employing said at least one pseudo classifier in an attempt to extract at least one value belonging to said previously extracted semantic category. - View Dependent Claims (8, 9)
-
-
10. A method for use in a method for understanding a natural language text, comprising performing the following selectively in a statistical manner:
-
attempting to extract at least one value belonging to a semantic category from a natural language text or a form thereof; and if a result of said attempting complies with a predetermined criterion, attempting to extract, based on said result, at least one value belonging to another semantic category of a different hierarchical level than said semantic category, else performing at least one action from a group of actions including;
asking a submitter of said text a question whose content depends on said result and giving up on understanding said natural language text;wherein said predetermined criterion is at least one from a group including;
at least one value for said semantic category was extracted, only one value for said semantic category was extracted, one of said at least one value extracted for said semantic category is selected based on a grade thereof, a correct number of values for said semantic category were extracted, a correct number of values for said semantic category are selected based on grades thereof from among said at least one value extracted for said semantic category, at least some values belonging to other previously extracted at least one semantic category are appropriate for at least one value extracted for said semantic category, values belonging to other previously extracted at least one semantic category are appropriate for only one value extracted for said semantic category, said semantic category is a particular semantic category where an unlimited number of extracted values is allowed, it is desired to process in parallel more than one extracted value for said semantic category, there is a default value corresponding to each required value for said semantic category which was not extracted, there is only one possible value for said semantic category, and there is only a correct number of possible values for said semantic category.
-
-
11. A method for understanding a natural language text, comprising:
- receiving a natural language text;
processing each at least two semantic categories, said each on a different hierarchical level, by performing the following selectively in a statistical manner; (i) attempting to determine at least one value belonging to said each semantic category through extraction, wherein if said each semantic category is not a first processed of said at least two semantic categories, then said attempting is based on results of previously processed semantic categories, and (ii) if said each semantic category is not a last processed of said at least two semantic categories and a result of said attempting does not comply with a predetermined criterion, dialoging with a submitter of said text and receiving at least one answer from said submitter, wherein at least one value determined from said at least one answer augments said result so as to comply with said predetermined criterion and allow extraction attempts for other of said at least two semantic categories to be subsequently processed; and evaluating values determined for said at least two semantic categories with respect to one another to determine whether said values are sufficient to understand said text, and if said values are not sufficient;
dialoging with said submitter, receiving at least one answer from said submitter, determining from said at least one answer at least one value belonging to at least one of said at least two semantic categories , said at least one value in conjunction with earlier determined values being sufficient to understand said text. - View Dependent Claims (12, 13)
- receiving a natural language text;
Specification