RAD: Reinforced Attention Decoder Model On Question Generation
Lists
Only you see this
Abstract
Question Generation (QG) aims to construct questions from given text automatically. Recently, QG has received widely concerned. The mainstream method is still based on the fixed sequence generation model of Seq2Seq model, and few people consider the influence of generation order in the result. In this paper, we present a novel Reinforced Attention Decoder Neural Network for the QA-SRL task. First, our model draws on the idea of the reinforcement learning algorithm with baseline, which is using the accuracy of each slot and sentence as the reward, updating the Policy Network to predict the optimal generation order. Second, we apply the Attention mechanism on the baseline to get more relevant information about the entire sentence. Addition experiments explore that distilling knowledge from RAD (the teacher) model to guide RAD-Reborn model (the student) training can achieve better performance. Extensive experiments on QA-SRL Bank 2.0 show that our model outperforms previous systems of all of the evaluation metrics. In particular, the metric EM (Exact Match) increased significantly by over 3%.
BibTeX
@inproceedings{li2020rad,
author = {Xin Li and Zhen Huang and Feng Liu and Changjian Wang and Minghao Hu and Shiyi Xu and Yuxing Peng},
title = {{RAD: Reinforced Attention Decoder Model On Question Generation}},
booktitle = {IJCNN},
year = {2020},
doi = {10.1109/ijcnn48605.2020.9207483},
}Loading related content...