期刊文献+

结合Bi-LSTM和注意力模型的问答系统研究 被引量:6

A QUESTION AND ANSWER SYSTEM BASED ON BI-LSTM AND ATTENTION MODEL
下载PDF
导出
摘要 针对传统的问答系统普遍存在回答准确率不高、语义识别能力差等问题,提出一种结合双向长短时记忆网络(Bi-LSTM)和注意力(Attention)模型的问答系统。利用生成的句向量,学习句子中的语义特征以及问答之间的匹配关系,获取上下文信息;融合注意力模型,能够找到对话的主题信息,从而为用户做出精准的回答。实验结果表明,该系统的回答准确率高于其他模型,可达到80.76%。 Traditional question and answer systems generally have problems such as low accuracy of answering and poor semantic recognition.In order to solve the above shortcomings,this paper proposes a question and answer system based on Bi-LSTM and attention model.By using the generated sentence vector,the system learned the semantic features of sentences and the matching relationship between questions and answers to get the context information.It integrated the attention model to find the topic information of the dialogue,so as to make accurate answers for the users.The experimental results show that the answer accuracy of our question and answer system is higher than other models,which can reach 80.76%.
作者 邵曦 陈明 Shao Xi;Chen Ming(College of Telecommunications and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,Jiangsu,China)
出处 《计算机应用与软件》 北大核心 2020年第10期52-56,共5页 Computer Applications and Software
基金 国家自然科学基金面上项目(61872199,61872424)。
关键词 深度学习 Bi-LSTM 注意力模型 句向量 问答系统 Deep learning Bi-LSTM Attention model Sentence vector Question and answer system
  • 相关文献

参考文献4

二级参考文献162

  • 1梅立军,周强,臧路,陈祖舜.知网与同义词词林的信息融合研究[J].中文信息学报,2005,19(1):63-70. 被引量:28
  • 2吴友政,赵军,段湘煜,徐波.问答式检索技术及评测研究综述[J].中文信息学报,2005,19(3):1-13. 被引量:48
  • 3董振东,董强,郝长伶.知网的理论发现[J].中文信息学报,2007,21(4):3-9. 被引量:99
  • 4.百度热门搜索[EB/OL].http://top.baidu.com,2005/03/18,[2005-05-17].
  • 5Lee T B. Semantic Web architecture[EB/OL]. 2000[2013- 07-25]. http://www. w3. org/2000/talks/1206-xmI2k-tbl. 2000-11-8.
  • 6Aditya P, Anand R, Hector G-M, Towards the Web of concepts: Extracting concepts from large datasets[C]//Proc of the 36th Int Conf on Very Large Data Bases VLDB'10. San Francisco, CA: Morgan Kaufmann, 2010: 566-577.
  • 7Gruber T R. A translations approach to portable ontology specifications[J]. Knowledge Acquisition, 1993,5(2): 199- 220.
  • 8Etzioni 0, Cafarella M, Downey D, et al. Unsupervised named-entity extraction from the Web: An experimental study[EB/OL]. 2005[2013-07-25]. https: //homes. cs. washington. edu/ etzioni/papers/knowitall-aij. pdf.
  • 9Etzioni 0, Cafarella M, Downey D, et al. Web-scale information extraction in knowitall , (preliminary results)[C]//Proc of the 13th Int Conf on World Wide Web. New York: ACM, 2004: 100-110.
  • 10Banko M, Cafarella M 1, Soderland S. et al. Open information extraction from the Web[C]//Proc of the 20th Int Joint Conf on Artifical Intelligence (I]CAI'07). New York: ACM, 2007: 2670-2676.

共引文献505

同被引文献36

引证文献6

二级引证文献8

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部