Detecting changes between documents using a machine learning classifier

1. A method for detecting changes between documents comprising:

training a machine learning classifier with one or more sections within an initial document to learn classifications for the sections, wherein the one or more sections of the initial document serve as the classifications;

applying one or more second sections of a second document to the machine learning classifier to classify the one or more second sections, wherein at least one second section lacks a classification and indicates a new section relative to the initial document; and

mapping the one or more second sections with a classification to the one or more sections of the initial document based on the classification of the one or more second sections.

2. The method of claim 1 , further comprising:

comparing the mapped sections to detect changes within the mapped one or more second sections relative to the one or more sections of the initial document; and

presenting the mapped one or more second sections indicating the detected changes.

3. The method of claim 1 , wherein the initial document includes a policy comprising a medical clinical trial.

4. The method of claim 3 , wherein the one or more sections include one or more conditions for patients to satisfy to participate in the medical clinical trial.

5. The method of claim 1 , wherein at least one classification is unmapped to the one or more second sections of the second document and indicates that a section associated with the at least one unmapped classification is absent in the second document.

6. The method of claim 4 , further comprising:

training a plurality of machine learning classifiers each with one or more conditions of a corresponding different policy within a corresponding initial document to learn classifications for the conditions, wherein the one or more conditions of the corresponding initial document serve as the classifications for the corresponding policy;

applying one or more second conditions of a corresponding second document for the corresponding policy to a machine learning classifier associated with the corresponding policy to classify the one or more second conditions; and

mapping the one or more second conditions to the one or more conditions of the corresponding initial document of the corresponding policy based on the classification of the one or more second conditions.

7. A system for detecting changes between documents comprising:

at least one processor configured to:

train a machine learning classifier with one or more sections within an initial document to learn classifications for the sections, wherein the one or more sections of the initial document serve as the classifications;

apply one or more second sections of a second document to the machine learning classifier to classify the one or more second sections, wherein at least one second section lacks a classification and indicates a new section relative to the initial document; and

map the one or more second sections with a classification to the one or more sections of the initial document based on the classification of the one or more second sections.

8. The system of claim 7 , wherein the at least one processor is further configured to:

compare the mapped sections to detect changes within the mapped one or more second sections relative to the one or more sections of the initial document; and

present the mapped one or more second sections indicating the detected changes.

9. The system of claim 7 , wherein the initial document includes a policy comprising a medical clinical trial, and wherein the one or more sections include one or more conditions for patients to satisfy to participate in the medical clinical trial.

10. The system of claim 7 , wherein at least one classification is unmapped to the one or more second sections of the second document and indicates that a section associated with the at least one unmapped classification is absent from the second document.

11. The system of claim 9 , wherein the at least one processor is further configured to:

train a plurality of machine learning classifiers each with one or more conditions of a corresponding different policy within a corresponding initial document to learn classifications for the conditions, wherein the one or more conditions of the corresponding initial document serve as the classifications for the corresponding policy;

apply one or more second conditions of a corresponding second document for the corresponding policy to a machine learning classifier associated with the corresponding policy to classify the one or more second conditions; and

map the one or more second conditions to the one or more conditions of the corresponding initial document of the corresponding policy based on the classification of the one or more second conditions.

12. A computer program product for detecting changes between documents, the computer program product comprising one or more computer readable storage media collectively having program instructions embodied therewith, the program instructions executable by at least one processor to cause the at least one processor to:

train a machine learning classifier with one or more sections within an initial document to learn classifications for the sections, wherein the one or more sections of the initial document serve as the classifications;

apply one or more second sections of a second document to the machine learning classifier to classify the one or more second sections, wherein at least one second section lacks a classification and indicates a new section relative to the initial document; and

map the one or more second sections with a classification to the one or more sections of the initial document based on the classification of the one or more second sections.

13. The computer program product of claim 12 , wherein the program instructions further cause the at least one processor to:

compare the mapped sections to detect changes within the mapped one or more second sections relative to the one or more sections of the initial document; and

present the mapped one or more second sections indicating the detected changes.

14. The computer program product of claim 12 , wherein the initial document includes a policy comprising a medical clinical trial.

15. The computer program product of claim 14 , wherein the one or more sections include one or more conditions for patients to satisfy to participate in the medical clinical trial.

16. The computer program product of claim 12 , wherein at least one classification is unmapped to the one or more second sections of the second document and indicates that a section associated with the at least one unmapped classification is absent from the second document.

17. The computer program product of claim 15 , wherein the program instructions further cause the at least one processor to:

train a plurality of machine learning classifiers each with one or more conditions of a corresponding different policy within a corresponding initial document to learn classifications for the conditions, wherein the one or more conditions of the corresponding initial document serve as the classifications for the corresponding policy;

apply one or more second conditions of a corresponding second document for the corresponding policy to a machine learning classifier associated with the corresponding policy to classify the one or more second conditions; and

map the one or more second conditions to the one or more conditions of the corresponding initial document of the corresponding policy based on the classification of the one or more second conditions.