Question Generation with Minimal Recursion Semantics

Question Generation (QG) is the task of generating reasonable questions from a text. It is a relatively new research topic and has its potential usage in intelligent tutoring systems and closed-domain question answering systems. Current approaches include template or syntax based methods. This thesis proposes a novel approach based entirely on semantics. Minimal Recursion Semantics (MRS) is a meta-level semantic representation with emphasis on scope underspecification. With the English Resource Grammar and various tools from the DELPH-IN community, a natural language sentence can be interpreted as an MRS structure by parsing, and an MRS structure can be realized as a natural language sentence through generation. There are three issues emerging from semantics-based QG: (1) sentence simplification for complex sentences, (2) question transformation for declarative sentences, and (3) generation ranking. Three solutions are also proposed: (1) MRS decomposition through a Connected Dependency MRS Graph, (2) MRS transformation from declarative sentences to interrogative sentences, and (3) question ranking by simple language models atop a MaxEnt-based model. The evaluation is conducted in the context of the Question Generation Shared Task and Generation Challenge 2010. The performance of proposed method is compared against other syntax and rule based systems. The result also reveals the challenges of current research on question generation and indicates direction for future work.