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.
For an up-to-date description of the techniques used in SEMAFOR, see:
- Frame-Semantic Parsing
Dipanjan Das, Desai Chen, André F. T. Martins, Nathan Schneider, and Noah A. Smith
In Computational Linguistics 40(1), March 2014.
This paper describes the algorithms used in SEMAFOR as of version 2.1.
- Frame-Semantic Role Labeling with Heterogeneous Annotations
Meghana Kshirsagar, Sam Thomson, Nathan Schneider, Jaime Carbonell, Noah A. Smith, and Chris Dyer
In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (ACL-IJCNLP), Beijing, China, July 2015.
This paper describes enhancements to SEMAFOR that are reflected in version 3.1.
Earlier descriptions appear in:
- An Exact Dual Decomposition Algorithm for Shallow Semantic Parsing with Constraints
Dipanjan Das, André F. T. Martins, and Noah A. Smith
In Proceedings of the Joint Conference on Lexical and Computational Semantics (*SEM 2012), Montréal, Québec, June 2012.
- Graph-Based Lexicon Expansion with Sparsity-Inducing Penalties
Dipanjan Das and Noah A. Smith
In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2012), Montréal, Québec, June 2012.
Semi-Supervised Frame-Semantic Parsing for Unknown Predicates
and Noah A. Smith
In Proceedings of Annual Meeting of the Association for Computational Linguistics (ACL 2011), Portland, OR, June 2011.
Probabilistic Frame-Semantic Parsing
Nathan Schneider, Desai Chen,
and Noah A. Smith
In Proceedings of the North American Chapter of the Association for Computational Linguistics Human Language Technologies Conference (NAACL 2010), Los Angeles, CA, June 2010.
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.