• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Computer speech and language >BERT syntactic transfer: A computational experiment on Italian, French and English languages
【24h】

BERT syntactic transfer: A computational experiment on Italian, French and English languages

机译：BERT句法转移：意大利，法语和英语语言的计算实验

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

This paper investigates the ability of multilingual BERT (mBERT) language model to transfer syntactic knowledge cross-lingually, verifying if and to which extent syntactic dependency relationships learnt in a language are maintained in other languages. In detail, the main contributions of this paper are: (ⅰ) an analysis of the cross-lingual syntactic transfer capability of mBERT model; (ⅱ) a detailed comparison of cross-language syntactic transfer among languages belonging to different branches of the Indo-European languages, namely English, Italian and French, which present very different syntactic constructions; (ⅲ) a study on the transferability of a syntactic phenomenon peculiar of Italian language, namely the pronoun dropping (pro-drop), also known as omissibility of the subject. To this end, a structural probe devoted to reconstruct the dependency parse tree of a sentence has been exploited, representing the input sentences with the contextual embeddings from mBERT layers. The results of the experimental assessment have shown a transfer of syntactic knowledge of the mBERT model among these languages. Moreover, the behaviour of the probe in the transition from pro-drop to non-pro-drop languages and vice versa has proven to be more effective in case of languages sharing a common linguistic matrix. The possibility of transferring syntactical knowledge, especially in the case of specific phenomena, meets both a theoretical need and can have important practical implications in syntactic tasks, such as dependency parsing.
机译：本文调查了多语言BERT（MBERT）语言模型转移句法知识的能力交叉，验证是否在语言中学到的句法依赖关系，以其他语言维护。详细地说，本文的主要贡献是：（Ⅰ）MBERT模型的交叉语法转移能力分析; （Ⅱ）属于印度欧洲语言不同分支的语言的跨语法转移的详细比较，即英语，意大利和法语，呈现出非常不同的句法结构; （Ⅲ）意大利语奇迹奇特的句法现象的可转移性研究，即代词丢弃（潜水），也称为受试者的遗漏。为此，已经利用了致专用用于重建句子的依赖性解析树的结构探测，其代表了来自Mbert层的上下文嵌入的输入句子。实验评估的结果显示出这些语言中Mbert模型的句法知识的转移。此外，探头在从Pro-Drop到非滴剂语言的转变中的行为，并且在共享共同语言矩阵的语言的情况下已经证明是更有效的。转移句法知识的可能性，特别是在特定现象的情况下，符合理论需求，并且可以在句法任务中具有重要的实际意义，例如依赖解析。

著录项

  • 来源
    《Computer speech and language》 |2022年第1期|101261.1-101261.19|共19页
  • 作者

    Raffaele Guarasci; Stefano Silvestri; Giuseppe De Pietro; Hamido Fujita; Massimo Esposito;

  • 作者单位

    Institute for High Performance Computing and Networking of National Research Council of Italy (ICAR-CNR) via Pietro Castellino 111 80131 Naples Italy;

    Institute for High Performance Computing and Networking of National Research Council of Italy (ICAR-CNR) via Pietro Castellino 111 80131 Naples Italy;

    Institute for High Performance Computing and Networking of National Research Council of Italy (ICAR-CNR) via Pietro Castellino 111 80131 Naples Italy;

    Iwate Prefecture University Takizawa Iwate Japan;

    Institute for High Performance Computing and Networking of National Research Council of Italy (ICAR-CNR) via Pietro Castellino 111 80131 Naples Italy;

  • 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

    Cross language; Dependency Parse Tree; Language models; Multilingual BERT; Transfer learning; Syntactic phenomena;

    机译：跨语言;依赖解析树;语言模型;多语种伯特;转移学习;句法现象;

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