@inproceedings{82b8aef03ddf4922a2271d4015425180,
title = "Graph-Enhanced Question Generation with Question Type Prediction and Statement Recovery",
abstract = "Question Generation (QG) is an essential task in natural language processing, which aims to generate grammatical questions for given sentences or paragraphs. This task focuses on understanding the structures and semantics of sentences. This paper proposes a graph-enhanced question generation model based on Variational Autoencoders (VAE). We construct a semantic graph by dependency parsing and then encode the graph by iteration of Gated Graph Neural Networks (GGNN). Then we get the graph-enhanced representation by fusing the sentence-level and graph-level representation to perform pre-training of statement recovery and joint training of question type prediction and generation. Experiments show promising results of our proposed model on the most extensively used Question Answering (QA) dataset SQuAD.",
keywords = "Gated Graph Neural Network, Multi-Task, Question Generation, Variational Autoencoder",
author = "Shichen Chen and Shumin Shi and Weiye Jiang",
note = "Publisher Copyright: {\textcopyright} 2023 ACM.; 7th International Conference on Control Engineering and Artificial Intelligence, CCEAI 2023 ; Conference date: 28-01-2023 Through 30-01-2023",
year = "2023",
month = jan,
day = "28",
doi = "10.1145/3580219.3580231",
language = "English",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery",
pages = "60--65",
editor = "Dan Zhang and Yong Yue",
booktitle = "Proceedings - 2023 7th International Conference on Control Engineering and Artificial Intelligence, CCEAI 2023",
}