Question Generation with Adaptive Copying Neural Networks

Public Deposited
Resource Type
  • Given the rapid development of communication technology, online business websites are becoming increasingly popular. However, it is time-consuming for customers to read long product reviews. Therefore, if we can generate questions that can be answered by extensive product specifications, customers could obtain their desired information easily. In this thesis, we aim to tackle the automatic question generation task. We proposed a novel network Adaptive Copying Neural Network (ACNN). The proposed model adds a copying mechanism component onto a bidirectional LSTM architecture to adaptively generate more suitable questions from the input data. Subsequently, we calculated the generated questions' summarization score to see if they could be answered by the reviews. In our evaluation experiments, we confirmed that our method can outperform baseline QG methods in terms of BLEU, ROUGE and human evaluation scores. In addition, we combined the summarization scores with our model, which resulted in a performance boost.

Thesis Degree Level
Thesis Degree Name
Thesis Degree Discipline
Rights Notes
  • Copyright © 2019 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, research, scholarship, and teaching. Theses may only be shared by linking to Carleton University Institutional Repository and no part may be used without proper attribution to the author. No part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner.
Date Created
  • 2019


In Collection: