SYSTEMS, METHODS, AND COMPUTER PROGRAM PRODUCTS FOR SLOT NORMALIZATION OF TEXT DATA

• US 20200134004A1
• Filed: 05/13/2019
• Published: 04/30/2020
• Est. Priority Date: 10/25/2018
• Status: Active Grant

• Current Assignee: Blackboiler, Inc.
• Original Assignee: BlackBoiler, LLC
• Inventors: SIMONSON, Daniel E., Herr, Jonathan, Avant, Joey T., Riedel, Garen P., Broderick, Daniel P.
• Granted Patent: US 10,614,157 B1
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/2379 Updates performed during online database operations; commit processing
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 40/106 Display of layout of documents; Previewing
• CPC Class Codes: G06F 40/166 Editing, e.g. inserting or deleting
• CPC Class Codes: G06F 40/174 Form filling; Merging
• CPC Class Codes: G06F 40/20 Natural language analysis semantic analysis of natural language G06F40/30
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

Methods, systems, and computer program products are provided for customization and insertion of a clause into an electronic document under analysis (DUA). The method includes the steps of receiving and electronic DUA, automatically detecting a slot type in the received DUA, assigning a DUA slot value to the detected slot type, and automatically updating one or more clauses in a clause library using the DUA slot value, wherein the updating includes inserting the DUA slot value into each slot in the one or more clauses having a slot type matching the detected slot type.

Claims

1. A computer-implemented method comprising:

receiving a training corpus comprising a plurality of documents, wherein each of the documents comprises one or more slot types;

normalizing each of the one or more slot types in the plurality of documents in the training corpus with a representation of a respective slot type;

obtaining a document under analysis (DUA);

automatically detecting a slot type in the DUA;

normalizing the detected slot type in the DUA with a representation of the detected slot type in the DUA; and

,

determining, using the training corpus and the normalized detected slot type in the DUA, an edit operation to apply to the DUA.

2. The method of claim 1, further comprising:

assigning a DUA slot value to the detected slot type in the DUA.

3. The method of claim 2, further comprising:

applying the determined edit operation to the DUA; and

,

replacing the representation of the detected slot type in the DUA with the assigned DUA slot value.

4. The method of claim 2, the method further comprising:

automatically updating one or more clauses in a clause library using the DUA slot value, wherein the updating comprises inserting the DUA slot value into each slot in the one or more clauses having a slot type matching the detected slot type.

5. The method of claim 4, further comprising:

displaying the DUA on a graphical user interface;

displaying the updated one or more clauses on the graphical user interface;

receiving an indication that a user has selected one of the displayed updated one or more clauses; and

inserting into the DUA the selected updated clause.

6. The method of claim 5, further comprising:

displaying the detected slot type and the assigned DUA slot value in the graphical user interface.

7. The method of claim 6, further comprising:

receiving an instruction to modify the DUA slot value from a user; and

,

automatically updating the one or more clauses in the clause library using the modified DUA slot value.

8. The method of claim 5, wherein the graphical user interface comprises a first area for displaying the DUA and a second area for displaying the updated one or more clauses, wherein the step of inserting into the DUA the selected updated clause comprises:

inserting the selected updated clause at a location of a cursor in the DUA displayed in the first area of the graphical user interface.

9. The method of claim 1, wherein automatically detecting a slot type in the DUA further comprises:

extracting a chain from the DUA;

affixing one or more slot types to the extracted chain, wherein the affixing results in a set of permutations, each permutation comprising one of the one or more slot types and the extracted chain;

submitting each of the permutations to a scoring function; and

,

associating one of the slot types to the extracted chain based on a value output from the scoring function.

10. The method of claim 1, further comprising:

receiving a set of annotations, the annotations comprising a surface form of each of the one or more slot types for each corresponding document in the training corpus.

11. The method of claim 1, further comprising:

tokenizing the DUA into one or more statements-under-analysis (SUAs);

obtaining from the training corpus a candidate original text;

obtaining from the training corpus a candidate final text associated with the candidate original text; and

,

determining the edit operation by aligning the SUA with at least one of the candidate original text and the candidate final text.

12. A non-transitory computer readable medium storing instructions configured to cause a computer to perform the method of claim 1.

13. A system comprising:

a processor;

a non-transitory computer readable memory coupled to the processor, wherein the processor is configured to;

receive a training corpus comprising a plurality of documents, wherein each of the documents comprises one or more slot types;

normalize each of the one or more slot types in the plurality of documents in the training corpus with a representation of a respective slot type;

obtain a document under analysis (DUA);

automatically detect a slot type in the DUA;

normalize the detected slot type in the DUA with a representation of the detected slot type in the DUA; and

determine, using the training corpus and the normalized detected slot type in the DUA, an edit operation to apply to the DUA.

14. The system of claim 13, wherein the processor is further configured to:

assign a DUA slot value to the detected slot type in the DUA.

15. The system of claim 14, wherein the processor is further configured to:

apply the determined edit operation to the DUA; and

,

replace the representation of the detected slot type in the DUA with the assigned DUA slot value.

16. The system of claim 14, wherein the processor is further configured to:

automatically update one or more clauses in a clause library using the DUA slot value, wherein the update comprises an insertion of the DUA slot value into each slot in the one or more clauses having a slot type matching the detected slot type.

17. The system of claim 16, further comprising:

a display device coupled to the processor,

wherein the processor is further configured to;

display the DUA on a graphical user interface of the display device;

display the updated one or more clauses on the graphical user interface;

receive an indication that a user has selected one of the displayed updated one or more clauses; and

insert into the DUA the selected updated clause.

18. The system of claim 13, wherein the processor is further configured to:

extract a chain from the DUA;

affix one or more slot types to the extracted chain, wherein the affixation results in a set of permutations, each permutation comprising one of the one or more slot types and the extracted chain;

submit each of the permutations to a scoring function; and

,

associate one of the slot types to the extracted chain based on a value output from the scoring function.

19. The system of claim 13, wherein the processor is further configured to:

receive a set of annotations, the annotations comprising a surface form of each of the one or more slot types for each corresponding document in the training corpus.

20. The system of claim 13, wherein the processor is further configured to:

tokenize the DUA into one or more statements-under-analysis (SUAs);

obtain from the training corpus a candidate original text;

obtain from the training corpus a candidate final text associated with the candidate original text; and

,

determine the edit operation by aligning the SUA with at least one of the candidate original text and the candidate final text.