• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE International Conference on Semantic Computing >A Context-Aware Approach for the Identification of Complex Words in Natural Language Texts
【24h】

A Context-Aware Approach for the Identification of Complex Words in Natural Language Texts

机译：上下文识别自然语言文本中复杂词的识别方法

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

摘要

This paper evaluates the effect of the context on the identification of complex words in natural language texts. The approach automatically tags words as either complex or not, based on two sets of features: base features that only pertain to the target word, and contextual features that take the context of the target word into account. We experimented with several supervised machine learning models, and trained and tested the approach with the SemEval-2016 dataset. Results show that considering contextual features significantly improves the identification of complex words by reaching an F-measure of 0.260 compared to 0.184 without them.
机译：本文评估了上下文对自然语言文本中复杂单词识别的影响。该方法基于两组功能自动将单词标记为复杂或不复杂：仅与目标单词相关的基本特征，以及将目标单词的上下文考虑在内的上下文特征。我们尝试了几种有监督的机器学习模型，并使用SemEval-2016数据集训练和测试了该方法。结果表明，考虑到上下文特征，F度量达到0.260相比F度量显着改善了复杂单词的识别，而没有度量则为0.184。

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