SEMAFOR is a frame-semantic parser developed by Dipanjan Das, Sam Thomson, Meghana Kshirsagar, André F. T. Martins, Nathan Schneider, Desai Chen, and Noah Smith.
Open-source software developed for research purposes, SEMAFOR automatically processes English sentences according to the form of semantic analysis in Berkeley FrameNet.


Source Code

There is now a SEMAFOR users' discussion list which should serve as a forum for questions. SEMAFOR's developers will monitor the list but cannot guarantee technical support.

You can also join the ARK-tools mailing list for announcements about software and datasets from the Noah's ARK lab.

Further Reading

For an up-to-date description of the techniques used in SEMAFOR, see:

Earlier descriptions appear in:

The following technical reports supply additional details:


This work was supported by DARPA grant NBCH-1080004, DARPA grant FA8750-12-2-0342 funded under the DEFT program, NSF grants IIS-0836431, IIS-0844507, IIS-0915187, and IIS-1054319, Google's support through the "Wordly Knowledge Project", Qatar National Research Fund grant NPRP08-485-1-083, computational resources provided by Yahoo and TeraGrid resources provided by the Pittsburgh Supercomputing Center under NSF grant number TG-DBS110003.

Please address questions, bug fixes, and comments to the SEMAFOR users' group or code repository.