基于迭代信息传递和滑动窗口注意力的问题生成模型研究(Question Generation Model Based on Iterative Message Passing and Sliding Windows Hierarchical Attention)
Qian Chen (陈千), Xiaoying Gao (高晓影), Suge Wang (王素格), Xin Guo (郭鑫)
Abstract
知识图谱问题生成任务是从给定的知识图谱中生成与其相关的问题。目前,知识图谱问题生成模型主要使用基于RNN或Transformer对知识图谱子图进行编码,但这种方式丢失了显式的图结构化信息,在解码器中忽视了局部信息对节点的重要性。本文提出迭代信息传递图编码器来编码子图,获取子图显式的图结构化信息,此外,我们还使用滑动窗口注意力机制提高RNN解码器,提升子图局部信息对节点的重要度。从WQ和PQ数据集上的实验结果看,我们提出的模型比KTG模型在BLEU4指标上分别高出2.16和15.44,证明了该模型的有效性。- Anthology ID:
- 2021.ccl-1.28
- Volume:
- Proceedings of the 20th Chinese National Conference on Computational Linguistics
- Month:
- August
- Year:
- 2021
- Address:
- Huhhot, China
- Editors:
- Sheng Li (李生), Maosong Sun (孙茂松), Yang Liu (刘洋), Hua Wu (吴华), Kang Liu (刘康), Wanxiang Che (车万翔), Shizhu He (何世柱), Gaoqi Rao (饶高琦)
- Venue:
- CCL
- SIG:
- Publisher:
- Chinese Information Processing Society of China
- Note:
- Pages:
- 293–303
- Language:
- Chinese
- URL:
- https://aclanthology.org/2021.ccl-1.28
- DOI:
- Cite (ACL):
- Qian Chen, Xiaoying Gao, Suge Wang, and Xin Guo. 2021. 基于迭代信息传递和滑动窗口注意力的问题生成模型研究(Question Generation Model Based on Iterative Message Passing and Sliding Windows Hierarchical Attention). In Proceedings of the 20th Chinese National Conference on Computational Linguistics, pages 293–303, Huhhot, China. Chinese Information Processing Society of China.
- Cite (Informal):
- 基于迭代信息传递和滑动窗口注意力的问题生成模型研究(Question Generation Model Based on Iterative Message Passing and Sliding Windows Hierarchical Attention) (Chen et al., CCL 2021)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2021.ccl-1.28.pdf