Modifying a set of instructions based on bootstrapped knowledge acquisition from a limited knowledge domain

Patent metadata

Field	Value
Publication number	US-11556803-B2
Application number	US-202016839677-A
Country	US
Kind code	B2
Filing date	Apr 3, 2020
Priority date	Nov 11, 2016
Publication date	Jan 17, 2023
Grant date	Jan 17, 2023

Abstract

Mechanisms for automatically modifying a set of instructions based on an expanded domain specific knowledge base is provided. The mechanisms generate a domain specific knowledge base comprising a set of entities and corresponding domain specific attributes and expand the domain specific knowledge base to include values for the domain specific attributes through an automated bootstrap learning process that performs natural language processing and analysis of natural language content using a set of pre-condition annotated action terms. The mechanisms receive electronic content comprising an initial set of instructions to perform an operation and evaluate the initial set of instructions based on the expanded domain specific knowledge base to identify a missing instruction. The mechanisms modify the initial set of instructions to include an additional instruction based on the missing instruction and thereby generate a modified set of instructions.

First claim

What is claimed is:

1. A method, in a data processing system comprising a processor and a memory accessible by the processor, for automatically modifying a set of instructions based on an expanded domain specific knowledge base, the method comprising:
generating, by the data processing system, a domain specific knowledge base comprising a set of entities and corresponding domain specific attributes;
expanding, by the data processing system, the domain specific knowledge base to include values for the corresponding domain specific attributes through an automated bootstrap learning process that performs natural language processing and analysis of natural language content using a set of pre-condition annotated action terms, thereby generating an expanded domain specific knowledge base;
receiving, by the data processing system, electronic content comprising an initial set of instructions to perform an operation;
evaluating, by the data processing system, the initial set of instructions, based on the expanded domain specific knowledge base, to identify at least one missing instruction that should be present in the initial set of instructions but is not present;
identifying, by the data processing system, one or more additional instructions for insertion into the initial set of instructions to perform actions to satisfy a requirement of the at least one missing instruction;
modifying, by the data processing system, the initial set of instructions to include the one or more additional instructions and thereby generate a modified set of instructions; and
outputting, by the data processing system, the modified set of instructions.

2. The method of claim 1 , wherein the electronic content is an electronic document of an electronic corpus, and wherein outputting the modified set of instructions comprises outputting a modified electronic document for inclusion in the electronic corpus.

3. The method of claim 1 , wherein evaluating the initial set of instructions based on the expanded domain specific knowledge base to identify at least one missing instruction comprises:
evaluating, for each instance of an entity specified in the initial set of instructions and a corresponding action specified in the initial set of instructions, whether a value of a domain specific attribute of the entity satisfies a pre-condition corresponding to a pre-condition annotation of a pre-condition annotated action term associated with the corresponding action; and
determining that there is a missing instruction for each instance of an entity and a corresponding action specified in the initial set of instructions where the value of the domain specific attribute of the entity does not satisfy the pre-condition corresponding to the pre-condition annotation of the pre-condition annotated action term associated with the corresponding action.

4. The method of claim 3 , wherein identifying one or more additional instructions for insertion into the initial set of instructions to perform actions to satisfy a requirement of the at least one missing instruction, comprises:
identifying, in an instruction knowledge base data structure, an additional instruction that generates a value of a domain specific attribute of an entity that satisfies the pre-condition corresponding to the pre-condition annotation of the pre-condition annotated action term associated with the corresponding action; and
retrieving the additional instruction from the instruction knowledge base data structure.

5. The method of claim 3 , further comprising:
maintaining, for each entity specified in the initial set of instructions, a temporal state of the entity, wherein the temporal state of the entity corresponds to a state of the entity that results from completion of a previous instruction in the initial set of instructions that operates on the entity, wherein evaluating, for each instance of an entity specified in the initial set of instructions and a corresponding action specified in the initial set of instructions, whether a value of a domain specific attribute of the entity satisfies a pre-condition corresponding to a pre-condition annotation of a pre-condition annotated action term associated with the corresponding action is performed based on the temporal state of the entity.

6. The method of claim 1 , wherein the automated bootstrap learning process associates a value with a domain specific attribute of an entity, in the set of entities, based on a pre-condition value of a pre-condition annotation of an instance of an action term, in the set of pre-condition annotated action terms, that is correlated with the entity in the natural language content.

7. The method of claim 1 , wherein outputting the modified set of instructions comprises outputting the modified set of instructions for implementation by an automated system to perform the operation, and wherein the method further comprises:
executing, by the automated system, the modified set of instructions to thereby perform the operation.

8. The method of claim 1 , wherein the entities in the set of entities are ingredients for cooking recipes, and wherein the action terms in the set of pre-condition annotated action terms are actions that are able to be performed on the ingredients, and wherein, for each pre-condition annotation action term in the set of pre-condition action terms, a pre-condition annotation of the pre-condition annotated action term specifies a state of matter of an ingredient required in order for a corresponding action to be correctly performed on the ingredient.

9. A computer program product comprising a non-transitory computer readable medium having a computer readable program stored therein, wherein the computer readable program, when executed on a data processing system, causes the data processing system to:
generate a domain specific knowledge base comprising a set of entities and corresponding domain specific attributes;
expand the domain specific knowledge base to include values for the corresponding domain specific attributes through an automated bootstrap learning process that performs natural language processing and analysis of natural language content using a set of pre-condition annotated action terms, thereby generating an expanded domain specific knowledge base;
receive electronic content comprising an initial set of instructions to perform an operation;
evaluate the initial set of instructions, based on the expanded domain specific knowledge base, to identify at least one missing instruction that should be present in the initial set of instructions but is not present;
identify one or more additional instructions for insertion into the initial set of instructions to perform actions to satisfy a requirement of the at least one missing instruction;
modify the initial set of instructions to include the one or more additional instructions and thereby generate a modified set of instructions; and
output the modified set of instructions.

10. The computer program product of claim 9 , wherein the electronic content is an electronic document of an electronic corpus, and wherein outputting the modified set of instructions comprises outputting a modified electronic document for inclusion in the electronic corpus.

11. The computer program product of claim 9 , wherein the computer readable program further causes the data processing system to evaluate the initial set of instructions based on the expanded domain specific knowledge base to identify at least one missing instruction at least by:
evaluating, for each instance of an entity specified in the initial set of instructions and a corresponding action specified in the initial set of instructions, whether a value of a domain specifi

Assignees

• IBM

Inventors

• Byron Donna K
• Johnson Benjamin L
• Tecuci Dan G

Classifications

• G06N5/02 Primary

  Knowledge representation; Symbolic representation · CPC title

• G06F40/30

  Semantic analysis · CPC title

• G06F40/40

  Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) · CPC title

• G06F40/56

  Natural language generation · CPC title

• G06N5/04

  Inference or reasoning models · CPC title