会议论文详细信息
2nd International Symposium on Application of Materials Science and Energy Materials
Using Multiple Encoders for Chinese Neural Question Generation from the Knowledge Base
材料科学;能源学
Chen, Meixi^1 ; Zhao, Jiahao^1 ; Liu, Ming^1
College of Computer and Information Science, Southwest University, Chongqing, China^1
关键词: Chinese question;    Diverse features;    Encoder-decoder;    Intelligent tutoring system;    Machine translations;    NAtural language processing;    Network frameworks;    Rule-based approach;   
Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/490/4/042013/pdf
DOI  :  10.1088/1757-899X/490/4/042013
学科分类:材料科学(综合)
来源: IOP
PDF
【 摘 要 】

Question generation is an important task in the field of natural language processing and intelligent tutoring system. Previous work on Chinese question generation focused on the rule-based approach, which requires a large amount of human resource to develop the question generation rules. With the recent success of deep neural network in natural language processing, especially the encoder-decoder neural network framework in machine translation, this study explored the effectiveness of the encoder-decoder network in Chinese question generation, where a triple from the knowledge base as an input is encoded and a question as the output is decoded. More importantly, the traditional encoder-decoder network is extended to have multiple encoders that can capture more diverse features to represent the triple. The study results showed that the model with multiple encoders outperformed the traditional encoder-decoder neural network by 1.78 BLEU points.

【 预 览 】
附件列表
Files Size Format View
Using Multiple Encoders for Chinese Neural Question Generation from the Knowledge Base 513KB PDF download
  文献评价指标  
  下载次数:15次 浏览次数:23次