[RETRACTED] Syn-QG: Syntactic and Shallow Semantic Rules for Question Generation

Kaustubh Dhole, Christopher D. Manning


Abstract
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 Syn-QG, 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.
Anthology ID:
2020.acl-main.69
Original:
2020.acl-main.69v1
Version 2:
2020.acl-main.69v2
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
752–765
Language:
URL:
https://aclanthology.org/2020.acl-main.69
DOI:
10.18653/v1/2020.acl-main.69
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2020.acl-main.69.pdf
Source:
 2020.acl-main.69.Source.zip
Dataset:
 2020.acl-main.69.Dataset.pdf
Video:
 http://slideslive.com/38929019
Data
SQuAD