Semantic framework for natural language programming
First Claim
Patent Images
1. A framework for generating a semantic interpretation of a natural language input received by a client application, the framework comprising:
- an interpreter that is stored as computer executable instructions on a computer readable storage medium, wherein the computer executable instructions are executed by a computer processor that is a component of a computing device, and wherein this execution of the computer readable instructions causes the interpreter to utilize the computer processor to communicate between the client application and a plurality of analysis engines; and
a linguistic object model comprising;
a first set of linguistic object model types that are adapted to define possible interpretations; and
a second set of linguistic object model types that are adapted to define actual interpretations from the possible interpretations;
wherein the first set of linguistic object model types and the second set of linguistic object model types are each independent of any particular natural language; and
a declarative schema associated with the client application and configured to be received by the interpreter from the client application, the declarative schema describing a semantic model of natural language features of the client application, wherein the semantic model includes a description of relationships among a plurality of semantic modeling types, and wherein at least a portion of the semantic modeling types are derived from the first and second sets of linguistic object model types;
wherein the interpreter is configured to be initialized with the declarative schema;
wherein the interpreter is configured to receive, from the plurality of analysis engines, a plurality of possible interpretations expressed in the first set of linguistic object model types, and wherein the plurality of possible interpretations are possible interpretations of the natural language input received by the client application; and
wherein the interpreter is configured to instantiate one of the second linguistic object model types for at least one of the plurality of possible interpretations that are determined to be an actual interpretation of the natural language input received by the client application.
1 Assignment
0 Petitions
Accused Products
Abstract
A framework for generating a semantic interpretation of natural language input includes an interpreter, a first set of types, and a second set of types. The interpreter is adapted to mediate between a client application and one or more analysis engines to produce interpretations of the natural language input that are valid for the client application. The first set of types is adapted to define interactions between the interpreter and the one or more analysis engines. The second set of types is adapted to define interactions between the interpreter and the client application.
40 Citations
16 Claims
-
1. A framework for generating a semantic interpretation of a natural language input received by a client application, the framework comprising:
-
an interpreter that is stored as computer executable instructions on a computer readable storage medium, wherein the computer executable instructions are executed by a computer processor that is a component of a computing device, and wherein this execution of the computer readable instructions causes the interpreter to utilize the computer processor to communicate between the client application and a plurality of analysis engines; and a linguistic object model comprising; a first set of linguistic object model types that are adapted to define possible interpretations; and a second set of linguistic object model types that are adapted to define actual interpretations from the possible interpretations; wherein the first set of linguistic object model types and the second set of linguistic object model types are each independent of any particular natural language; and a declarative schema associated with the client application and configured to be received by the interpreter from the client application, the declarative schema describing a semantic model of natural language features of the client application, wherein the semantic model includes a description of relationships among a plurality of semantic modeling types, and wherein at least a portion of the semantic modeling types are derived from the first and second sets of linguistic object model types; wherein the interpreter is configured to be initialized with the declarative schema; wherein the interpreter is configured to receive, from the plurality of analysis engines, a plurality of possible interpretations expressed in the first set of linguistic object model types, and wherein the plurality of possible interpretations are possible interpretations of the natural language input received by the client application; and wherein the interpreter is configured to instantiate one of the second linguistic object model types for at least one of the plurality of possible interpretations that are determined to be an actual interpretation of the natural language input received by the client application. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A framework, in a computer system having a processor and memory, for instantiating an interpretation of a natural language input to natural language features of a client application, the framework comprising:
-
a linguistic object model comprising; a first set of linguistic object model types that are adapted to define possible interpretations; and a second set of linguistic object model types that are adapted to define actual interpretations from the possible interpretations; wherein the first set of linguistic object model types and the second set of linguistic object model types are each independent of any particular natural language; and an interpreter configured to be implemented by the processor executing computer readable instructions from the memory, and further configured to be initialized with declarative schema associated with the client application and received by the interpreter from the client application, the declarative schema describing a semantic model of natural language features of the client application, wherein the semantic model includes a description of relationships among a plurality of semantic modeling types. and wherein at least a portion of the semantic modeling types are derived from the first and second sets of linguistic object model types; wherein the interpreter is adapted to receiver a natural language input and to communicate with one or more natural language analysis engines to produce interpretations of the natural language input by resolving possible interpretations received from the one or more analysis engines against the declarative schema; and wherein the interpreter is adapted to instantiate one or more of the resolved interpretations in the client application. - View Dependent Claims (8, 9, 10)
-
-
11. A natural language processing framework comprising:
-
an interpreter that is stored as computer executable instructions on a computer readable storage medium, wherein the computer executable instructions are configured to be executed by a computer processor that is a component of a computing device, and wherein this execution of the computer readable instructions causes the interpreter to utilize the computer processor to communicate between a client application and a plurality of analysis engines; a linguistic object model comprising; a first set of linguistic object model types that are adapted to define possible interpretations; and a second set of linguistic object model types that are adapted to define actual interpretations from the possible, interpretations; wherein the first set of linguistic object model types and the second set of linguistic object model types are each independent of any particular natural language; and a declarative schema associated with the client application and received by the interpreter from the client application, the declarative schema describing a semantic model of natural language features of the client application, wherein the semantic model includes a description of relationships among a plurality of semantic modeling types, and wherein at least a portion of the semantic modeling types are derived from the first and second sets of linguistic object model types; wherein the interpreter is configured to be initialized with the declarative schema and resolves, against the declarative schema, a plurality of possible interpretations received from the plurality of natural language analysis engines as possible interpretations of the natural language input; and wherein the interpreter is configured to instantiate one type of the second set of linguistic object model types in the client application for at least one of the plurality of possible interpretations that are determined, as a result of said resolution of the plurality of possible interpretations against the declarative schema, to be an actual interpretation of the natural language input received by the client application, said actual interpretation being one of said interpretations of the natural language input that are valid for the client application. - View Dependent Claims (12, 13, 14, 15, 16)
-
Specification