Identifying and ranking potentially privileged documents using a machine learning topic model

1. A computer-implemented method for identifying and ranking potentially privileged documents using a machine learning topic model, at least a portion of the method being performed by a computer system comprising one or more processors, the method comprising:

receiving, by the computer system, a set of documents;

for each documents in the set of documents:

extracting, by the computer system, a set of spans from the document,

generating, by the computer system using a Latent Dirichlet Allocation machine learning topic model, a set of topics, and a subset of legal topics in the set of topics, for the set of spans,

generating, by the computer system, a vector of probabilities for each span in the set of spans with a probability being assigned to each topic in the set of topics for the span,

assigning, by the computer system, a score to one or more spans in the set of spans by summing the probabilities in the vector that are assigned to a topic in the subset of legal topics, and

assigning, by the computer system, a score to the document, the score indicating a potential that the document is privileged, the score being equal to a highest score of the scores assigned to the one or more spans in the set of spans; and

ranking, by the computer system, the documents based on the scores assigned to the documents.

2. The method of claim 1 , further comprising:

labelling, by the computer system, a first document in the set of documents as potentially privileged if the first document has a score above a certain threshold.

3. The method of claim 1 , further comprising:

generating, by the computer system, a master set of topics for the documents in the set of documents, the set of topics being a subset of the master set of topics.

4. The method of claim 1 , wherein the assigning, by the computer system, of a score to the one or more spans in the set of spans is not performed for a first span of the one or more spans in the set of spans if at least one of: a language of the first span is unknown or cannot be detected, a number of tokens in the first span is less than a threshold, and the number of tokens in the first span is less than the threshold after names are removed from the first span.

5. The method of claim 1 , further comprising:

altering, by the computer system, the score assigned to a first span if a sender or a recipient of a document containing the first span is a legal entity.

6. The method of claim 1 , further comprising:

altering, by the computer system, the score assigned to a first document in the set of documents if a sender or a recipient of the first document is a legal entity.

7. The method of claim 1 , further comprising:

altering, by the computer system, the score assigned to a first span if the first span contains a mention of a legal entity.

8. The method of claim 1 , further comprising:

altering, by the computer system, the score assigned to a first document if the first document contains a mention of a legal entity.

9. The method of claim 8 , further comprising:

creating, by the computer system, a hypergraph comprising a set of entities based on communications between the set of entities in the set of documents; and

weighting, by the computer system, an edge between one or more entities in the set of entities if the communications between the one or more entities is potentially privileged.

10. The method of claim 9 , further comprising:

altering, by the computer system, the score assigned to a second document in the set of documents if the second document is a communication between entities with a weighted edge in the hypergraph.

11. One or more non-transitory computer-readable media comprising one or more computer-readable instructions that, when executed by one or more processors of a computer system, cause the computer system to perform a method for identifying and ranking potentially privileged documents, the method comprising:

receiving, by the computer system, a set of documents;

for each documents in the set of documents:

extracting, by the computer system, a set of spans from the document,

generating, by the computer system using a Latent Dirichlet Allocation machine learning topic model, a set of topics, and a subset of legal topics in the set of topics, for the set of spans,

generating, by the computer system, a vector of probabilities for each span in the set of spans with a probability being assigned to each topic in the set of topics for the span,

assigning, by the computer system, a score to one or more spans in the set of spans by summing the probabilities in the vector that are assigned to a topic in the subset of legal topics, and

assigning, by the computer system, a score to the document, the score indicating a potential that the document is privileged, the score being equal to a highest score of the scores assigned to the one or more spans in the set of spans; and

ranking, by the computer system, the documents based on the scores assigned to the documents.

12. The one or more non-transitory computer-readable media of claim 11 , wherein the method further comprises:

labelling, by the computer system, a first document in the set of documents as potentially privileged if the first document has a score above a certain threshold.

13. The one or more non-transitory computer-readable media of claim 11 , wherein the method further comprises:

generating, by the computer system, a master set of topics for the documents in the set of documents, the set of topics being a subset of the master set of topics.

14. The one or more non-transitory computer-readable media of claim 11 , wherein the assigning, by the computer system, of a score to the one or more spans in the set of spans is not performed for a first span of the one or more spans in the set of spans if at least one of: a language of the first span is unknown or cannot be detected, a number of tokens in the first span is less than a threshold, and the number of tokens in the first span is less than the threshold after names are removed from the first span.

15. The one or more non-transitory computer-readable media of claim 11 , wherein the method further comprises:

altering, by the computer system, the score assigned to a first span if a sender or a recipient of a document containing the first span is a legal entity.

16. The one or more non-transitory computer-readable media of claim 11 , wherein the method further comprises:

altering, by the computer system, the score assigned to a first document in the set of documents if a sender or a recipient of the first document is a legal entity.

17. The one or more non-transitory computer-readable media of claim 11 , wherein the method further comprises:

altering, by the computer system, the score assigned to a first span if the first span contains a mention of a legal entity.

18. The one or more non-transitory computer-readable media of claim 11 , wherein the method further comprises:

altering, by the computer system, the score assigned to a first document if the first document contains a mention of a legal entity.

19. The one or more non-transitory computer-readable media of claim 18 , wherein the method further comprises:

creating, by the computer system, a hypergraph comprising a set of entities based on communications between the set of entities in the set of documents; and

weighting, by the computer system, an edge between one or more entities in the set of entities if the communications between the one or more entities is potentially privileged.

20. The one or more non-transitory computer-readable media of claim 19 , wherein the method further comprises:

altering, by the computer system, the score assigned to a second document in the set of documents if the second document is a communication between entities with a weighted edge in the hypergraph.