For we who have had to roll some of the same functionality piecemeal out of tools like the Stanford NLP Core, tregex/tsurgeon, Wordnet, Beautiful Soup, and python nlptk, this looks on the surface to be pretty sweet. BSD licensing.
Here's a cool application - tagging negation and speculation clauses in some text (their demo has been trained on biomedical text):
Example sentence:
When U937 cells were infected with HIV-1, no induction of NF-KB factor was detected, whereas high level of progeny virions was produced, suggesting that this factor was not required for viral replication.
Result:
When U937 cells were infected with HIV-1 , [NEG0 no induction of NF-KB factor was detected NEG0] , whereas high level of progeny virions was produced , [SPEC2 suggesting that this factor was [NEG1 not required for viral replication NEG1] SPEC2] .
Here's a cool application - tagging negation and speculation clauses in some text (their demo has been trained on biomedical text):
Example sentence: When U937 cells were infected with HIV-1, no induction of NF-KB factor was detected, whereas high level of progeny virions was produced, suggesting that this factor was not required for viral replication.
Result: When U937 cells were infected with HIV-1 , [NEG0 no induction of NF-KB factor was detected NEG0] , whereas high level of progeny virions was produced , [SPEC2 suggesting that this factor was [NEG1 not required for viral replication NEG1] SPEC2] .