• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>China National Conference on Computational Linguistics >Mongolian Questions Classification Based on Multi-Head Attention
【24h】

Mongolian Questions Classification Based on Multi-Head Attention

机译：蒙古问题基于多针关注的分类

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Question classification is a crucial subtask in question answering system. Mongolian is a kind of few resource language. It lacks public labeled corpus. And the complex morphological structure of Mongolian vocabulary makes the data-sparse problem. This paper proposes a classification model, which combines the Bi-LSTM model with the Multi-Head Attention mechanism. The Multi-Head Attention mechanism extracts relevant information from different dimensions and representation subspace. According to the characteristics of Mongolian word-formation, this paper introduces Mongolian morphemes representation in the embedding layer. Morpheme vector focuses on the semantics of the Mongolian word. In this paper, character vector and morpheme vector are concatenated to get word vector, which sends to the Bi-LSTM getting context representation. Finally, the Multi-Head Attention obtains global information for classification. The model experimented on the Mongolian corpus. Experimental results show that our proposed model significantly outperforms baseline systems.
机译：问题分类是问题应答系统的重要子任务。蒙古族是一种资源语言。它缺乏公众标记的语料库。而蒙古语词汇的复杂形态结构使得数据稀疏问题。本文提出了一种分类模型，它将BI-LSTM模型与多针注意机构相结合。多主题注意机制从不同维度和表示子空间中提取相关信息。根据蒙古文字的特点，本文介绍了嵌入层中的蒙古语素表示。语素矢量侧重于蒙古词的语义。在本文中，字符向量和语素矢量被连接以获取Word Vector，它发送到Bi-LSTM获取上下文表示。最后，多主题注意到分类的全局信息。模型在蒙古语料库上实验。实验结果表明，我们所提出的模型显着优于基线系统。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号