Role-oriented risk checking in contract review based on deep semantic association analysis

1. A computer-implemented method for automatic statement compliance replacement in a contract, comprising:

generating, by a processor device using deep semantic association analysis by a neural network, a report specifying a set of potential risks relating to explicit and hidden roles of involved parties to the contract by

categorizing input statements of the contract into respective obligation/right pairs according to a deep semantic association distribution of the input statements, each of the respective obligation/right pairs including a respective obligation and a respective right from a set of obligations and a set of rights, wherein the deep semantic association distribution associates the obligations with an action, an agent performing the action, and temporal, spatial, and context constraints on the obligations;

detecting deep semantic differences beyond superficial wording between the respective obligation/right pairs and a set of reference obligation/right pairs;

identifying the explicit and hidden roles of the involved parties in the respective obligations/rights pairs according to domain-specific use scenarios and multidimensional local and global context clues in the contract;

identifying the set of potential risks relating to the explicit and hidden roles of the involved parties by applying a deep semantic role-oriented risk entailment model that stores role-oriented rules to the deep semantic differences; and

automatically replacing, by a machine, respective ones of the input statements violating a set of compliance requirements with compliant input statements in compliance with the set of compliance requirements, responsive to the set of potential risks relating to the explicit and hidden roles of the involved parties violating the set of compliance requirements.

2. The computer-implemented method of claim 1 , wherein the report further specifies the explicit and hidden roles of the involved parties.

3. The computer-implemented method of claim 1 , wherein (i) the hidden roles of the involved parties and (ii) the potential risks relating to the hidden roles, are emphasized in the report to enhance a visibility of the hidden roles and the potential risks relating to the hidden roles.

4. The computer-implemented method of claim 1 , wherein said categorizing step comprises characterizing each of the obligations by key semantic elements extracted from the set of obligations.

5. The computer-implemented method of claim 1 , wherein said categorizing step comprises associating the obligations with an action, an agent performing the action, and temporal, spatial, and context constraints.

6. The computer-implemented method of claim 1 , wherein said detecting step comprises:

identifying matches between semantic elements in respective obligation/right pairs and the set of reference obligation/right pairs; and

identifying the deep semantic differences between the respective obligation/right pairs and matching ones of the reference obligation/right pairs.

7. The computer-implemented method of claim 1 , further comprising determining whether the respective obligation/right pairs are compliant with a set of compatibility requirements, and modifying the respective obligation/right pairs to be compliant responsive to a determination of non-compliance.

8. The computer-implemented method of claim 1 , further comprising replacing any of the obligation/right pairs with replacement obligation/right pairs that implicate a revised set of potential risks that is in compliance with a set of compliance requirements, responsive to the set of potential risks relating to the explicit and hidden roles of the involved parties violating the set of compliance requirements.

9. The computer-implemented method of claim 1 , wherein the set of compliance requirements comprises an expected amount of processing resources, a format, and an expected processing time.

10. A computer program product for automatic statement compliance replacement in a contract, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising:

generating, by a processor device of the computer using deep semantic association analysis, a report specifying a set of potential risks relating to explicit and hidden roles of involved parties to the contract by

categorizing input statements of the contract into respective obligation/right pairs according to a deep semantic association distribution of the input statements, each of the respective obligation/right pairs including a respective obligation and a respective right from a set of obligations and a set of rights, wherein the deep semantic association distribution associates the obligations with an action, an agent performing the action, and temporal, spatial, and context constraints on the obligations;

detecting deep semantic differences beyond superficial wording between the respective obligation/right pairs and a set of reference obligation/right pairs;

identifying the explicit and hidden roles of the involved parties in the respective obligations/rights pairs according to domain-specific use scenarios and multidimensional local and global context clues in the contract;

identifying the set of potential risks relating to the explicit and hidden roles of the involved parties by applying a deep semantic role-oriented risk entailment model that stores role-oriented rules to the deep semantic differences; and

automatically replacing, by a machine, respective ones of the input statements violating a set of compliance requirements with compliant input statements in compliance with the set of compliance requirements, responsive to the set of potential risks relating to the explicit and hidden roles of the involved parties violating the set of compliance requirements.

11. The computer program product of claim 10 , wherein the report further specifies the explicit and hidden roles of the involved parties.

12. The computer program product of claim 10 , wherein (i) the hidden roles of the involved parties and (ii) the potential risks relating to the hidden roles, are emphasized in the report to enhance a visibility of the hidden roles and the potential risks relating to the hidden roles.

13. The computer program product of claim 10 , wherein said categorizing step comprises characterizing each of the obligations by key semantic elements extracted from the set of obligations.

14. The computer program product of claim 10 , wherein said categorizing step comprises associating the obligations with an action, an agent performing the action, and temporal, spatial, and context constraints.

15. The computer program product of claim 10 , wherein said detecting step comprises:

identifying matches between semantic elements in respective obligation/right pairs and the set of reference obligation/right pairs; and

identifying the deep semantic differences between the respective obligation/right pairs and matching ones of the reference obligation/right pairs.

16. The computer program product of claim 10 , wherein the method further comprises determining whether the respective obligation/right pairs are compliant with a set of compatibility requirements, and modifying the respective obligation/right pairs to be compliant responsive to a determination of non-compliance.

17. The computer program product of claim 10 , wherein the method further comprises replacing any of the obligation/right pairs with replacement obligation/right pairs that implicate a revised set of potential risks that is in compliance with a set of compliance requirements, responsive to the set of potential risks relating to the explicit and hidden roles of the involved parties violating the set of compliance requirements.

18. A computer processing system for automatic statement compliance replacement in a contract, comprising:

a memory for storing program code; and

a processor device for running the program code to generate, using deep semantic association analysis, a report specifying a set of potential risks relating to explicit and hidden roles of involved parties to the contract by

categorizing input statements of the contract into respective obligation/right pairs according to a deep semantic association distribution of the input statements, each of the respective obligation/right pairs including a respective obligation and a respective right from a set of obligations and a set of rights, wherein the deep semantic association distribution associates the obligations with an action, an agent performing the action, and temporal, spatial, and context constraints on the obligations;

detecting deep semantic differences beyond superficial wording between the respective obligation/right pairs and a set of reference obligation/right pairs;

identifying the explicit and hidden roles of the involved parties in the respective obligations/rights pairs according to domain-specific use scenarios and multidimensional local and global context clues in the contract;

identifying the set of potential risks relating to the explicit and hidden roles of the involved parties by applying a deep semantic role-oriented risk entailment model that stores role-oriented rules to the deep semantic differences; and

automatically replacing respective ones of the input statements violating a set of compliance requirements with compliant input statements in compliance with the set of compliance requirements, responsive to the set of potential risks relating to the explicit and hidden roles of the involved parties violating the set of compliance requirements.