Interfacing Systemic Functional Grammars with Frame Semantics
Presented at the 45th International Systemic Functional Congress (ISFC 2018), Boston, MA (July 2018).
As computational applications play a greater role in society, Systemic Functional Linguistics can play an important role in producing effective interactions between those applications and the people who use them. Significant progress has been made in the fields of computational representations of semantics (e.g., FrameNet, Ruppenhofer et al., 2006) and automated semantic reasoning (e.g., the Semantic Web, Berners-Lee et al., 2001), and it will be important for computational systems based on Systemic Functional Grammars (SFGs) to integrate with these semantic representations.
During this talk, we present an elegant interface between SFGs and the semantic frame representations used in artificial intelligence in general, and by systems such as FrameNet in particular. The interface is based on new realization rules that are the semantic analogs of lexification and preselection in current systemic functional linguistic theory.
This new semantic interface is implemented as part of the SFG Toolkit being developed by Charles River Analytics. We describe the new realization rules and how they map between the grammar and semantic frames. We also provide several examples of how the SFG Toolkit uses the new realization rules and semantic frames to automatically generate and interpret sentences that are both syntactically and semantically complex.
1 Harvard University
2 Charles River Analytics
For More InformationTo learn more or request a copy of a paper (if available), contact Terry Patten.
(Please include your name, address, organization, and the paper reference. Requests without this information will not be honored.)