Non-standard and standard clause detection
A non-standard and standard clause detection system imports raw input data or contractual documents, and extracts non-standard and standard clauses that are semantically linked. One embodiment of a disclosed configuration is a system and a method for identifying non-standard and standard clauses in contractual documents. The system and the method comprise of generating a primary policy and a secondary policy, obtaining a first feature data set by applying the primary policy to a semantic language evaluator, and obtaining a second feature data set by applying the secondary policy to the semantic language evaluator. The first feature data set obtained is the aggregation of the standard clauses used in the document. Furthermore, the second feature data set encompasses the first feature data set, thus the difference between the first feature data set and the second feature data set is the aggregation of the non-standard clauses.
1. A computer implemented method of identifying non-standard clauses and standard clauses in a document comprised of a plurality of original clauses, the method comprising:
generating a primary policy comprising primary rules, primary features, primary clause examples, and a first threshold for use in a semantic language evaluator to generate a plurality of feature replaced clauses by replacing each of the plurality of original clauses with the primary features and to compare each of the plurality of feature replaced clauses according to the primary policy to provide a first feature data set comprising the standard clauses;
generating a secondary policy comprising the primary features, the primary clause examples, and a second threshold for use in the semantic language evaluator to compare each of the plurality of feature replaced clauses according to the secondary policy to provide a second feature data set encompassing the first feature data set;
obtaining a difference data set comprising a difference between the first feature data set and the second feature data set, the difference data set comprising the non-standard clauses; and
providing an output comprising the standard clauses and the non-standard clauses.
2. The method of claim 1 , further comprising:
generating a predefined policy comprising predefined rules, predefined features, and predefined clause examples from a discovery engine;
providing for display the predefined policy to an end user; and
generating the primary policy comprising the primary features, the primary clause examples, and the first threshold provided by the end user.
3. The method of claim 1 , further comprising:
comparing each of the plurality of feature replaced clauses according to the primary policy in the semantic language evaluator;
generating a plurality of first degree of similarities for each of the plurality of feature replaced clauses according to the primary policy in the semantic language evaluator; and
providing the first feature data set comprising a first portion of the plurality of feature replaced clauses comprising the plurality of first degree of similarities greater than the first threshold.
4. The method of claim 3 , further comprising:
comparing each of the plurality of feature replaced clauses according to the secondary policy in the semantic language evaluator;
generating a plurality of second degree of similarities for each of the plurality of feature replaced clauses according to the secondary policy in the semantic language evaluator; and
providing the second feature data set comprising a second portion of the plurality of features replaced clauses comprising the plurality of second degree of similarities greater than the second threshold, the second threshold lower than the first threshold.
5. A computer implemented method for identifying non-standard clauses and standard clauses in a document comprised of a plurality of original clauses, the method comprising:
generating a primary policy for use in a semantic language evaluator to provide a first feature data set comprising the standard clauses;
generating a secondary policy for use in the semantic language evaluator to provide a second feature data set encompassing the first feature data set; and
obtaining a difference data set comprising a difference between the first feature data set and the second feature data set, the difference data set comprising the non-standard clauses.
6. The method of claim 5 , further comprising:
generating a predefined policy comprising predefined rules, predefined features, and predefined clause examples from a discovery engine;
providing for display the predefined policy to an end user;
generating the primary policy comprising primary rules, primary features, primary clause examples and a first threshold provided by the end user; and
generating the secondary policy comprising the primary features, the primary clause examples and a second threshold provided by the end user.
7. The method of claim 6 , further comprising:
generating a plurality of feature replaced clauses by replacing each of the plurality of original clauses with the primary features;
comparing each of the plurality of clauses according to the primary policy;
generating a plurality of first degree of similarities for each of the plurality of clauses according to the primary policy in the semantic language evaluator; and
providing the first feature data set comprising a first portion of the plurality of clauses, the first portion of the plurality of clauses comprising the plurality of first degree of similarities greater than the first threshold.
8. The method of claim 7 , further comprising:
comparing each of the plurality of features replaced clauses according to the secondary policy in the semantic language evaluator;
generating a plurality of second degree of similarities for each of the plurality of feature replaced clauses according to the secondary policy in the semantic language evaluator; and
providing the second feature data set comprising a second portion of the plurality of features replaced clauses comprising the plurality of second degree of similarities greater than the second threshold lower than the first threshold.
9. The method of claim 5 , further comprising providing for display an output comprising the standard clauses and the non-standard clauses to an end user.
10. A non-transitory computer readable medium configured to store program code, the program code comprising instructions that when executed by a processor cause the processor to:
generate a primary policy for use in a semantic language evaluator to provide a first feature data set comprising standard clauses;
generate a secondary policy for use in the semantic language evaluator to provide a second feature data set encompassing the first feature data set; and
obtain a difference data set comprising a difference between the first feature data set and the second feature data set, the difference data set comprising non-standard clauses.
11. The non-transitory computer readable medium of claim 10 , further comprising the program code that cause the processor to:
generate a predefined policy comprising predefined rules, predefined features, and predefined clause examples from a discovery engine;
provide for display the predefined policy to an end user;
generate the primary policy comprising primary rules, primary features, primary clause examples and a first threshold provided by the end user; and
generate the secondary policy comprising the primary features, the primary clause examples and a second threshold provided by the end user.
12. The non-transitory computer readable medium of claim 11 , further comprising the program code that cause the processor to:
generate a plurality of feature replaced clauses by replacing each of a plurality of original clauses with the primary features;
compare each of the plurality of clauses according to the primary policy;
generate a plurality of first degree of similarities for each of the plurality of clauses according to the primary policy in the semantic language evaluator; and
provide the first feature data set comprising a first portion of the plurality of clauses, the first portion of the plurality of clauses comprising the plurality of first degree of similarities greater than the first threshold.
13. The non-transitory computer readable medium of claim 12 , further comprising the program code that cause the processor to:
compare each of the plurality of clauses according to the secondary policy in the semantic language evaluator;
generate a plurality of second degree of similarities for each of the plurality of clauses according to the secondary policy in the semantic language evaluator; and
provide the second feature data set comprising a second portion of the plurality of feature replaced clauses comprising the plurality of second degree of similarities greater than the second threshold lower than the first threshold.
14. The non-transitory computer readable medium of claim 10 , further comprising the program code that cause the processor to:
provide for display an output comprising standard clauses and non-standard clauses to an end user.
15. A non-transitory computer readable medium configured to store program code, the program code comprising instructions that when executed by a processor cause the processor to:
generate a primary policy comprising primary rules, primary features, primary clause examples, and a first threshold for use in a semantic language evaluator to generate a plurality of feature replaced clauses by replacing each of a plurality of original clauses with the primary features and to compare each of the plurality of feature replaced clauses according to the primary policy to provide a first feature data set comprising standard clauses;
generate a secondary policy comprising the primary features, the primary clause examples, and a second threshold for use in the semantic language evaluator to compare each of the plurality of feature replaced clauses according to the secondary policy to provide a second feature data set encompassing the first feature data set;
obtain a difference data set comprising a difference between the first feature data set and the second feature data set, the difference data set comprising non-standard clauses; and
provide an output comprising the standard clauses and the non-standard clauses.
16. The non-transitory computer readable medium of claim 15 , further comprising the program code that cause the processor to:
generate a predefined policy comprising predefined rules, predefined features, and predefined clause examples from a discovery engine;
provide for display the predefined policy to an end user; and
generate the primary policy comprising the primary features, the primary clause examples, and the first threshold provided by the end user.
17. The non-transitory computer readable medium of claim 15 , further comprising the program code that cause the processor to:
compare each of the plurality of feature replaced clauses according to the primary policy in the semantic language evaluator;
generate a plurality of first degree of similarities for each of the plurality of feature replaced clauses according to the primary policy in the semantic language evaluator; and
provide the first feature data set comprising a first portion of the plurality of feature replaced clauses comprising the plurality of first degree of similarities greater than the first threshold.
18. The non-transitory computer readable medium of claim 17 , further comprising the program code that cause the processor to:
compare each of the plurality of feature replaced clauses according to the secondary policy in the semantic language evaluator;
generate a plurality of second degree of similarities for each of the plurality of feature replaced clauses according to the secondary policy in the semantic language evaluator; and
provide the second feature data set comprising a second portion of the plurality of features replaced clauses comprising the plurality of second degree of similarities greater than the second threshold, the second threshold lower than the first threshold.