Skip Navigation
York U: Redefine the PossibleHOME | Current Students | Faculty & Staff | Research | International
Search »FacultiesLibrariesCampus MapsYork U OrganizationDirectorySite Index
Future Students, Alumni & Visitors
2019 Technical Reports

Context-Aware Question and Answer Generation from Car Manuals

Elnaz Delpisheh, Muath Alzghool, Aijun An, Heidar Davoudi, Marjan Delpisheh, Emad Gohari and Sedigheh Mahdavi

Technical Report EECS-2019-01

York University

August 15, 2019

Abstract

We present a framework for automatically generating questions and answers (QAs) from text documents. The core of our proposed method utilizes rules on top of semantic role labels, which are easy to comprehend and maintain and effective in generating grammatically correct questions. In addition, we utilize advanced NLP techniques, such as text summarization (to avoid similar questions), word embedding (for context disambiguation), and topic modeling (to filter out irrelevant questions). We compare our method with the state-of-the-art methods for QA generation on car manuals and discuss our results.

Download paper in PDF format.



The documents distributed by this server have been provided by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a noncommercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.