Playbook generation using controlled causal language modeling
AssigneeInternational Business Machines Corporation
InventorsMehant Kammakomati, Prince Kumar, Ashok Pon Kumar Sree Prakash, Srikanth Govindaraj Tamilselvam, Padmanabha Venkatagiri Seshadri
Life of this patent
Estimating the term…
Abstract
Methods and systems for generating a playbook include parsing a prompt and playbook context to identify modules. Names of identified modules are added to the prompt to create a modified prompt. A document relevant to the playbook context and the modified prompt is identified based on a semantic search. A schema is determined based on the document. An automatic completion of the prompt is generated in accordance with the schema using a trained model.
Claims20
A method of generating a playbook, comprising:
- parsing a prompt and playbook context to identify modules;
- adding names of the identified modules to the prompt to create a modified prompt;
- identifying a document relevant to the playbook context and the modified prompt based on a semantic search;
- determining a schema based on the document;
- and
- generating an automatic completion of the prompt in accordance with the schema using a trained model including enforcing constraints to control outputs during inference of the trained model with logit processors selected for respective fields in the schema.
A system for generating a playbook, comprising:
- a hardware processor;
- and
- a memory that stores a computer program which, when executed by the hardware processor, causes the hardware processor to:
- parse a prompt and playbook context to identify modules;
- add names of the identified modules to the prompt to create a modified prompt;
- identify a document relevant to the playbook context and the modified prompt based on a semantic search;
- determine a schema based on the document;
- and
- generate an automatic completion of the prompt in accordance with the schema using a trained model including enforcing constraints to control outputs during inference of the trained model with logit processors selected for respective fields in the schema.
A computer program product for generating a playbook, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions being executable by a hardware processor to cause the hardware processor to:
- parse a prompt and playbook context to identify modules;
- add names of the identified modules to the prompt to create a modified prompt;
- identify a document relevant to the playbook context and the modified prompt based on a semantic search;
- determine a schema based on the document;
- and
- generate an automatic completion of the prompt in accordance with the schema using a trained model including enforcing constraints to control outputs during inference of the trained model with logit processors selected for respective fields in the schema.
Dependencies are inferred from the claim text.