• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Annual meeting of the Association for Computational Linguistics >Morphological Irregularity Correlates with Frequency
【24h】

Morphological Irregularity Correlates with Frequency

机译：形态不规则性与频率相关

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

摘要

We present a study of morphological irregularity. Following recent work, we define an information-theoretic measure of irregularity based on the predictability of forms in a language. Using a neural transduction model, we estimate this quantity for the forms in 28 languages. We first present several val-idatory and exploratory analyses of irregularity. We then show that our analyses provide evidence for a correlation between irregularity and frequency: higher frequency items are more likely to be irregular and irregular items are more likely be highly frequent. To our knowledge, this result is the first of its breadth and confirms longstanding proposals from the linguistics literature. The correlation is more robust when aggregated at the level of whole paradigms—providing support for models of linguistic structure in which inflected forms are unified by abstract underlying stems or lexemes. Code is available at https://github.com/shijie-wueural-transducer.
机译：我们提出了形态不规则性的研究。在最近的工作之后，我们根据语言中形式的可预测性定义了信息理论上对不规则性的度量。使用神经转导模型，我们估算了28种语言形式的数量。我们首先介绍几种对不规则性的验证和探索性分析。然后，我们表明，我们的分析为不规则与频率之间的相关性提供了证据：频率较高的项目更有可能是不规则的，而不规则项目则更有可能是频繁的。据我们所知，这一结果是其广度的第一，并证实了语言学文献中的长期建议。当在整个范式层次上进行聚合时，相关性更强健-为语言结构模型提供支持，在该语言结构模型中，变形形式由抽象的基础词干或词素统一。可以在https://github.com/shijie-wu/neural-transducer上找到代码。

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