...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neurocomputing >Leveraging bilingually-constrained synthetic data via multi-task neural networks for implicit discourse relation recognition
【24h】

Leveraging bilingually-constrained synthetic data via multi-task neural networks for implicit discourse relation recognition

机译：通过多任务神经网络利用双语约束的合成数据进行隐式话语关系识别

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Recognizing implicit discourse relations is an important but challenging task in discourse understanding. To alleviate the shortage of labeled data, previous work automatically generates synthetic implicit data (SynData) as additional training data, by removing connectives from explicit discourse instances. Although SynData has been proven useful for implicit discourse relation recognition, it also has the meaning shift problem and the domain problem. In this paper, we first propose to use bilingually-constrained synthetic implicit data (BiSynData) to enrich the training data, which can alleviate the drawbacks of SynData. Our BiSynData is constructed from a bilingual sentence-aligned corpus according to the implicit/explicit mismatch between different languages. Then we design a multi-task neural network model to incorporate our BiSynData to benefit implicit discourse relation recognition. Experimental results on both the English PDTB and Chinese CDTB data sets show that our proposed method achieves significant improvements over baselines using SynData. (C) 2017 Published by Elsevier B.V.
机译：认知内隐的话语关系是话语理解中一项重要但具有挑战性的任务。为了减轻标记数据的不足，以前的工作通过从显式话语实例中删除连接词，自动生成了合成隐式数据（SynData）作为附加的训练数据。尽管已证明SynData可用于隐式话语关系识别，但它也具有含义转移问题和领域问题。在本文中，我们首先提出使用双语约束的合成隐式数据（BiSynData）来丰富训练数据，这可以减轻SynData的缺点。根据不同语言之间的隐式/显式不匹配，我们的BiSynData是根据双语句子对齐的语料库构建的。然后，我们设计了一个多任务神经网络模型，以结合我们的BiSynData以使隐式话语关系识别受益。在英语PDTB和中文CDTB数据集上的实验结果表明，我们提出的方法比使用SynData的基线有了显着改善。 （C）2017由Elsevier B.V.发布

著录项

  • 来源
    《Neurocomputing》 |2017年第21期|69-79|共11页
  • 作者

    Wu Changxing; Shi Xiaodong; Chen Yidong; Huang Yanzhou; Su Jinsong;

  • 作者单位

    Xiamen Univ, Fujian Key Lab Brain Like Intelligent Syst, Xiamen 361005, Fujian, Peoples R China|Xiamen Univ, Sch Informat Sci & Technol, Dept Cognit Sci, Xiamen 361005, Fujian, Peoples R China;

    Xiamen Univ, Fujian Key Lab Brain Like Intelligent Syst, Xiamen 361005, Fujian, Peoples R China|Xiamen Univ, Sch Informat Sci & Technol, Dept Cognit Sci, Xiamen 361005, Fujian, Peoples R China;

    Xiamen Univ, Fujian Key Lab Brain Like Intelligent Syst, Xiamen 361005, Fujian, Peoples R China|Xiamen Univ, Sch Informat Sci & Technol, Dept Cognit Sci, Xiamen 361005, Fujian, Peoples R China;

    Xiamen Univ, Fujian Key Lab Brain Like Intelligent Syst, Xiamen 361005, Fujian, Peoples R China|Xiamen Univ, Sch Informat Sci & Technol, Dept Cognit Sci, Xiamen 361005, Fujian, Peoples R China;

    Xiamen Univ, Sch Software, Xiamen 361005, Fujian, Peoples R China;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Bilingually-constrained synthetic implicit data; Multi-task learning; Implicit discourse relation recognition; Neural network;

    机译：双语约束的合成隐含数据;多任务学习;内隐语篇关系识别;神经网络;

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