Syn-QG: Syntactic and Shallow Semantic Rules for Question Generation
This work addresses question generation for natural language processing applications, but it is incremental as it builds on existing syntactic and semantic parsing techniques.
The authors tackled the problem of generating questions from declarative sentences by developing SynQG, a rule-based system using syntactic and shallow semantic parsing, which produced more grammatical and relevant questions than previous systems, with back-translation improving grammaticality but slightly increasing irrelevant outputs.
Question Generation (QG) is fundamentally a simple syntactic transformation; however, many aspects of semantics influence what questions are good to form. We implement this observation by developing SynQG, a set of transparent syntactic rules leveraging universal dependencies, shallow semantic parsing, lexical resources, and custom rules which transform declarative sentences into question-answer pairs. We utilize PropBank argument descriptions and VerbNet state predicates to incorporate shallow semantic content, which helps generate questions of a descriptive nature and produce inferential and semantically richer questions than existing systems. In order to improve syntactic fluency and eliminate grammatically incorrect questions, we employ back-translation over the output of these syntactic rules. A set of crowd-sourced evaluations shows that our system can generate a larger number of highly grammatical and relevant questions than previous QG systems and that back-translation drastically improves grammaticality at a slight cost of generating irrelevant questions.