• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>3rd workshop on representation learning for NLP 2018 >Exploiting Common Characters in Chinese and Japanese to Learn Cross-lingual Word Embeddings via Matrix Factorization
【24h】

Exploiting Common Characters in Chinese and Japanese to Learn Cross-lingual Word Embeddings via Matrix Factorization

机译：利用汉语和日语的共同字符通过矩阵分解学习跨语言单词嵌入

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

Learning vector space representation of words (i.e., word embeddings) has recently attracted wide research interests, and has been extended to cross-lingual scenario. Currently most cross-lingual word embedding learning models are based on sentence alignment, which inevitably introduces much noise. In this paper, we show in Chinese and Japanese, the acquisition of semantic relation among words can benefit from the large number of common characters shared by both languages; inspired by this unique feature, we design a method named C.TC targeting to generate cross-lingual context of words. We combine C.TC with GloVe based on matrix factorization, and then propose an integrated model named CJ-Glo. Taking two sentence-aligned models and CJ-BOC (also exploits common characters but is based on CBOW) as baseline algorithms, we compare them with CJ-Glo on a series of NLP tasks including cross-lingual synonym, word analogy and sentence alignment. The result indicates CJ-Glo achieves the best performance among these methods, and is more stable in cross-lingual tasks: moreover, compared with CJ-BOC, CJ-Glo is less sensitive to the alteration of parameters.
机译：学习单词的向量空间表示（即单词嵌入）最近引起了广泛的研究兴趣，并且已经扩展到跨语言场景。当前，大多数跨语言的单词嵌入学习模型都是基于句子对齐的，这不可避免地会引入很多噪音。在本文中，我们用中文和日语显示，单词之间的语义关系的获得可以受益于两种语言共享的大量公共字符；受此独特功能的启发，我们设计了一种名为C.TC定位的方法来生成单词的跨语言上下文。我们基于矩阵分解将C.TC与GloVe相结合，然后提出一个名为CJ-Glo的集成模型。以两个句子对齐模型和CJ-BOC（也利用共同字符但基于CBOW）作为基准算法，我们将它们与CJ-Glo在一系列NLP任务（包括跨语言同义词，单词类比和句子对齐）上进行比较。结果表明，CJ-Glo在这些方法中达到了最佳性能，并且在跨语言任务中更稳定：此外，与CJ-BOC相比，CJ-Glo对参数更改不那么敏感。

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