Methods and systems for intelligent editing of legal documents

1. An apparatus for intelligent editing of legal documents, the apparatus comprising:

a processor; and

a memory communicatively connected to the processor, the memory containing instructions configuring the processor to:

access a plurality of legal source texts from a plurality of legal sources;

generate a score for each of the plurality of legal source texts;

train a plurality of natural language processing models as a function of the plurality of scored legal source texts and a first machine-learning process, wherein:

a first natural language processing model of the plurality of natural language processing models is trained by a first group of the plurality of scored legal source texts; and

a second natural language processing model of the plurality of natural language processing models is trained by a second group of the plurality of scored legal source texts;

receive user inputted legal text from a user device being operated by a human user to create a user legal document;

analyze the user inputted legal text using the plurality of natural language processing models; and

suggest, as a function of the analyzing, a modification to a target text of the user inputted legal text, wherein suggesting the modification to the target text further comprises outputting a suggested modification to the user inputted legal text to the user device.

2. The apparatus of claim 1 , wherein:

the first group of the plurality of scored legal source texts comprises high quality legal source texts; and

the second group of the plurality of scored legal source texts comprises non-legal texts.

3. The apparatus of claim 1 , wherein:

analyzing the user inputted legal text using the plurality of natural language processing modules comprises identifying at least instance of passive voice within the user inputted legal text; and

suggesting a modification to a target text of the user inputted legal text, comprises suggesting removal of the at least an instance of passive voice.

4. The apparatus of claim 1 , wherein the memory contains instructions further configuring the processor to train an n-gram model using n-gram training data comprising text corpora.

5. The apparatus of claim 4 , wherein the memory contains instructions further configuring the processor to determine a probability of a string of words from the user-inputted legal text using the n-gram model.

6. The apparatus of claim 1 , wherein training a plurality of natural language processing models comprises training a higher-order natural language processing model of the plurality of natural language processing modules, wherein the higher-order natural language processing model uses higher-order n-grams.

7. The apparatus of claim 6 , wherein the higher-order n-grams are on the order of at least 4-grams.

8. The apparatus of claim 1 , wherein the memory contains instructions further configuring the processor to:

receive a modified user legal document; and

generate a score for the modified user legal document, wherein generating the score for the modified user legal document comprises:

calculating a number of function words in the modified user legal document;

calculating a number of content words in the modified user legal document; and

generating the score for the modified user legal document, wherein the score is a ratio of the number of function words to the number of content words.

9. The apparatus of claim 1 , wherein the memory contains instructions further configuring the processor to:

receive a modified user legal document; and

generate a score for the modified user legal document, wherein generating the score for the modified user legal document comprises generating a heatmap for the modified user legal document, wherein the heatmap comprises sentiment ratings for a plurality of sentences of the modified user legal document.

10. The apparatus of claim 1 , wherein the memory contains instructions further configuring the processor to:

receive a modified user legal document; and

generate a score for the modified user legal document, wherein the score comprises a lexical density score of the modified user legal document.

11. A method for intelligent editing of legal documents, the method comprising:

accessing, by a processor, a plurality of legal source texts from a plurality of legal sources;

generating, by the processor, a score for each of the plurality of legal source texts;

training, by the processor, a plurality of natural language processing models as a function of the plurality of scored legal source texts and a first machine-learning process, wherein:

a first natural language processing model of the plurality of natural language processing models is trained by a first group of the plurality of scored legal source texts; and

a second natural language processing model of the plurality of natural language processing models is trained by a second group of the plurality of scored legal source texts;

receiving, by the processor, user inputted legal text from a user device being operated by a human user to create a user legal document;

analyzing, by the processor, the user inputted legal text using the plurality of natural language processing models; and

suggesting, by the processor, as a function of the analyzing, a modification to a target text of the user inputted legal text, wherein suggesting the modification to the target text further comprises outputting a suggested modification to the user inputted legal text to the user device.

12. The method of claim 11 , wherein:

the first group of the plurality of scored legal source texts comprises high quality legal source texts; and

the second group of the plurality of scored legal source texts comprises non-legal texts.

13. The method of claim 11 , wherein:

analyzing the user inputted legal text using the plurality of natural language processing modules comprises identifying at least instance of passive voice within the user inputted legal text; and

suggesting a modification to a target text of the user inputted legal text, comprises suggesting removal of the at least an instance of passive voice.

14. The method of claim 11 , further comprising training, by the processor, an n-gram model using n-gram training data comprising text corpora.

15. The method of claim 14 , further comprising determining, by the processor, a probability of a string of words from the user-inputted legal text using the n-gram model.

16. The method of claim 11 , wherein training a plurality of natural language processing models comprises training a higher-order natural language processing model of the plurality of natural language processing modules, wherein the higher-order natural language processing model uses higher-order n-grams.

17. The method of claim 16 , wherein the higher-order n-grams are on the order of at least 4-grams.

18. The method of claim 11 , further comprising:

receiving, by the processor, a modified user legal document; and

generating, by the processor, a score for the modified user legal document, wherein

generating the score for the modified user legal document comprises:

calculating a number of function words in the modified user legal document;

calculating a number of content words in the modified user legal document; and

generating the score for the modified user legal document, wherein the score is a ratio of the number of function words to the number of content words.

19. The method of claim 11 , further comprising:

receiving a modified user legal document; and

generating a score for the modified user legal document, wherein generating the score for the modified user legal document comprises generating a heatmap for the modified user legal document, wherein the heatmap comprises sentiment ratings for a plurality of sentences of the modified user legal document.

20. The method of claim 11 , further comprising:

receiving a modified user legal document; and

generating a score for the modified user legal document, wherein the score comprises a lexical density score of the modified user legal document.