Dynamic fact contextualization in support of artificial intelligence (AI) model development
Provided are techniques for dynamic fact contextualization in support of AI model development. A template from a plurality of templates is selected, where the template includes definitions for identifying facts. The facts are retrieved from a facts repository based on the definitions. It is determined that that the facts are valid based on one or more policies. A FactSheet is generated using the template and the facts. A machine learning model is used to identify one or more deficient facts from the FactSheet. The FactSheet is displayed in a preview with the one or more deficient facts. One or more facts corresponding to the one or more deficient facts are located. The FactSheet is updated to correct the one or more deficient facts with the corresponding facts.
1 . A computer-implemented method, comprising operations for:
selecting a template from a plurality of templates, wherein the template includes definitions for identifying facts;
retrieving the facts from a facts repository based on the definitions;
determining that the facts are valid based on one or more policies;
generating a FactSheet using the template and the facts;
using a machine learning model to identify one or more deficient facts from the FactSheet;
displaying the FactSheet in a preview with the one or more deficient facts;
locating one or more facts corresponding to the one or more deficient facts; and
updating the FactSheet to correct the one or more deficient facts with the corresponding facts.
2 . The computer-implemented method of claim 1 , further comprising operations for:
receiving new facts from a plurality of fact producers using a plurality of tools, and
dynamically updating the FactSheet.
3 . The computer-implemented method of claim 1 , further comprising operations for:
inputting a fact, a fact definition, and metadata into a system to generate one or more outputs from a group comprising: suggestions, examples, and supporting information about the fact; and
displaying the one or more outputs.
4 . The computer-implemented method of claim 3 , wherein the one or more outputs comprise one or more of: an explanation as to why a missing fact is required, an approach on how to provide the missing fact, and an example of the missing fact.
5 . The computer-implemented method of claim 1 , further comprising operations for:
displaying the FactSheet with a plurality of FactSheets;
in response to selection of the FactSheet, displaying the FactSheet in a new preview; and
enabling interaction with the FactSheet via the new preview.
6 . The computer-implemented method of claim 1 , wherein the one or more deficient facts comprise one or more invalid facts, one or more missing facts or both one or more invalid facts and one or more missing facts.
7 . The computer-implemented method of claim 1 , wherein the preview is displayed in a user tool.
8 . A computer program product, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform operations for:
selecting a template from a plurality of templates, wherein the template includes definitions for identifying facts;
retrieving the facts from a facts repository based on the definitions;
determining that the facts are valid based on one or more policies;
generating a FactSheet using the template and the facts;
using a machine learning model to identify one or more deficient facts from the FactSheet;
displaying the FactSheet in a preview with the one or more deficient facts;
locating one or more facts corresponding to the one or more deficient facts; and
updating the FactSheet to correct the one or more deficient facts with the corresponding facts.
9 . The computer program product of claim 8 , wherein the program instructions are executable by the processor to cause the processor to perform further operations for:
receiving new facts from a plurality of fact producers using a plurality of tools, and
dynamically updating the FactSheet.
10 . The computer program product of claim 8 , wherein the program instructions are executable by the processor to cause the processor to perform further operations for:
inputting a fact, a fact definition, and metadata into a system to generate one or more outputs from a group comprising: suggestions, examples, and supporting information about the fact; and
displaying the one or more outputs.
11 . The computer program product of claim 10 , wherein the one or more outputs comprise one or more of: an explanation as to why a missing fact is required, an approach on how to provide the missing fact, and an example of the missing fact.
12 . The computer program product of claim 8 , wherein the program instructions are executable by the processor to cause the processor to perform further operations for:
displaying the FactSheet with a plurality of FactSheets;
in response to selection of the FactSheet, displaying the FactSheet in a new preview; and
enabling interaction with the FactSheet via the new preview.
13 . The computer program product of claim 8 , wherein the one or more deficient facts comprise one or more invalid facts, one or more missing facts or both one or more invalid facts and one or more missing facts.
14 . The computer program product of claim 8 , wherein the preview is displayed in a user tool.
15 . A computer system, comprising:
one or more processors, one or more computer-readable memories and one or more computer-readable, tangible storage devices; and
program instructions, stored on at least one of the one or more computer-readable, tangible storage devices for execution by at least one of the one or more processors via at least one of the one or more computer-readable memories, to perform operations comprising:
selecting a template from a plurality of templates, wherein the template includes definitions for identifying facts;
retrieving the facts from a facts repository based on the definitions;
determining that the facts are valid based on one or more policies;
generating a FactSheet using the template and the facts;
using a machine learning model to identify one or more deficient facts from the FactSheet;
displaying the FactSheet in a preview with the one or more deficient facts;
locating one or more facts corresponding to the one or more deficient facts; and
updating the FactSheet to correct the one or more deficient facts with the corresponding facts.
16 . The computer system of claim 15 , wherein the operations further comprise:
receiving new facts from a plurality of fact producers using a plurality of tools, and
dynamically updating the FactSheet.
17 . The computer system of claim 15 , wherein the operations further comprise:
inputting a fact, a fact definition, and metadata into a system to generate one or more outputs from a group comprising: suggestions, examples, and supporting information about the fact; and
displaying the one or more outputs.
18 . The computer system of claim 17 , wherein the one or more outputs comprise one or more of: an explanation as to why a missing fact is required, an approach on how to provide the missing fact, and an example of the missing fact.
19 . The computer system of claim 15 , wherein the operations further comprise:
displaying the FactSheet with a plurality of FactSheets;
in response to selection of the FactSheet, displaying the FactSheet in a new preview; and
enabling interaction with the FactSheet via the new preview.
20 . The computer system of claim 15 , wherein the one or more deficient facts comprise one or more invalid facts, one or more missing facts or both one or more invalid facts and one or more missing facts.