Automatically constructing lexicons from unlabeled datasets
A system, method, and computer-readable medium are disclosed for performing a lexicon construction operation. The lexicon construction operation includes: identifying a corpus, the corpus comprising a plurality of training events, each of the plurality of training events comprising a term; grouping terms from the plurality of training events into topic clusters; analyzing the plurality of topic clusters, the analyzing providing a plurality of classified clusters; and, deriving a plurality of learned lexicons from the plurality of classified clusters.
1. A computer-implementable method for constructing a lexicon, comprising:
identifying a corpus, the corpus comprising a plurality of training events, each of the plurality of training events comprising a term;
grouping terms from the plurality of training events into topic clusters;
analyzing the plurality of topic clusters, the analyzing providing a plurality of classified clusters;
deriving a plurality of learned lexicons from the plurality of classified clusters;
storing the plurality of learned lexicons in a repository of lexicon data; and,
performing a security operation via a security analytics system, the security analytics system executing on a hardware processor of an information handling system, the security operation using the plurality of learned lexicons to perform an entity behavior detection operation.
2. The method of claim 1 , wherein:
an event of the plurality of event comprises unstructured data.
3. The method of claim 1 , further comprising:
receiving a stream of events, the stream of events comprising a plurality of monitored events;
performing an entity behavior detection operation, the entity behavior detection operation classifying the plurality of events using the plurality of learned lexicons.
4. The method of claim 3 , further comprising:
performing a security analytics operation on the plurality of events, the security analytics operation analyzing terms contained within the plurality of events based upon the plurality of learned lexicons.
5. The method of claim 3 , further comprising:
providing the plurality of classified events as additional training events to tune the learned lexicons.
6. The method of claim 1 , wherein:
the grouping of terms from the plurality of training events into topic clusters is performed via a topic mapping operation.
7. A system comprising:
a processor;
a data bus coupled to the processor; and
a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus, the computer program code interacting with a plurality of computer operations and comprising instructions executable by the processor and configured for:
identifying a corpus, the corpus comprising a plurality of training events, each of the plurality of training events comprising a term;
grouping terms from the plurality of training events into topic clusters;
analyzing the plurality of topic clusters, the analyzing providing a plurality of classified clusters;
deriving a plurality of learned lexicons from the plurality of classified clusters;
storing the plurality of learned lexicons in a repository of lexicon data; and,
performing a security operation via a security analytics system, the security analytics system executing on the processor, the security operation using the plurality of learned lexicons to perform an entity behavior detection operation.
8. The system of claim 7 , wherein:
an event of the plurality of event comprises unstructured data.
9. The system of claim 7 , wherein the instructions are further configured for:
receiving a stream of events, the stream of events comprising a plurality of monitored events;
performing an entity behavior detection operation, the entity behavior detection operation classifying the plurality of events using the plurality of learned lexicons.
10. The system of claim 9 , wherein the instructions are further configured for:
performing a security analytics operation on the plurality of events, the security analytics operation analyzing terms contained within the plurality of events based upon the plurality of learned lexicons.
11. The system of claim 9 , wherein the instructions are further configured for:
providing the plurality of classified events as additional training events to tune the learned lexicons.
12. The system of claim 7 , wherein:
the grouping of terms from the plurality of training events into topic clusters is performed via a topic mapping operation.
13. A non-transitory, computer-readable storage medium embodying computer program code, the computer program code comprising computer executable instructions configured for:
identifying a corpus, the corpus comprising a plurality of training events, each of the plurality of training events comprising a term;
grouping terms from the plurality of training events into topic clusters;
analyzing the plurality of topic clusters, the analyzing providing a plurality of classified clusters;
deriving a plurality of learned lexicons from the plurality of classified clusters;
storing the plurality of learned lexicons in a repository of lexicon data; and,
performing a security operation via a security analytics system, the security analytics system executing on a hardware processor of an information handling system, the security operation using the plurality of learned lexicons to perform an entity behavior detection operation.
14. The non-transitory, computer-readable storage medium of claim 13 , wherein:
an event of the plurality of event comprises unstructured data.
15. The non-transitory, computer-readable storage medium of claim 13 , wherein the computer executable instructions are further configured for:
receiving a stream of events, the stream of events comprising a plurality of monitored events;
performing an entity behavior detection operation, the entity behavior detection operation classifying the plurality of events using the plurality of learned lexicons.
16. The non-transitory, computer-readable storage medium of claim 15 , wherein the computer executable instructions are further configured for:
performing a security analytics operation on the plurality of events, the security analytics operation analyzing terms contained within the plurality of events based upon the plurality of learned lexicons.
17. The non-transitory, computer-readable storage medium of claim 15 , wherein the computer executable instructions are further configured for:
providing the plurality of classified events as additional training events to tune the learned lexicons.
18. The non-transitory, computer-readable storage medium of claim 13 , wherein:
the grouping of terms from the plurality of training events into topic clusters is performed via a topic mapping operation.
19. The non-transitory, computer-readable storage medium of claim 13 , wherein the computer executable instructions are deployable to a client system from a server system at a remote location.
20. The non-transitory, computer-readable storage medium of claim 13 , wherein the computer executable instructions are provided by a service provider to a user on an on-demand basis.