<listing id="kephd"></listing>
<tt id="kephd"></tt>

  • <label id="kephd"></label>
    <meter id="kephd"></meter>

    云南民族大學學報(自然科學版)

    2020, v.29;No.122(04) 366-370

    [打印本頁] [關閉]
    本期目錄(Current Issue) | 過刊瀏覽(Past Issue) | 高級檢索(Advanced Search)

    基于句法差異的漢-越平行句對抽取
    Chinese-Vietnamese parallel sentence pair extraction based on syntactic differences

    于志強;高明虎;陳宇星;
    YU Zhi-qiang;GAO Ming-hu;CHEN Yu-xing;Information and Network Center,Yunnan Minzu University;

    摘要(Abstract):

    低資源環境下,受限于平行語料的規模和質量,神經機器翻譯的效果并不理想.漢-越神經機器翻譯作為典型的低資源型機器翻譯,同樣面臨平行語料匱乏的問題.針對這一問題提出了基于句法差異的漢-越平行句對抽取方法.一方面,分析了漢語和越南語間的句法差異,通過詞性標簽對差異進行表述;另一方面,利用孿生結構的循環神經網絡,在編碼過程中融入句法差異信息,從句法規則角度更好的指導抽取過程.實驗表明,基于漢越可比語料所提方法能夠有效地抽取出高質量漢越平行句對.
    It has been shown that the performance of neural machine translation(NMT) drops starkly in low-resource conditions due to the scale and quality limit of parallel corpus. As a typical low-resource machine translation task, Chinese-Vietnamese neural machine translation also faces the same problem. This paper proposes a method of extraction of Chinese-Vietnamese parallel sentences based on syntactic differences. We first analyze the syntactic features between Chinese and Vietnamese, and express the differences by part-of-speech labels. Then we use the Siamese recurrent neural network to integrate syntactic features of the information into the coding process, and argue that this helps guide the extraction process. Experiments show that the proposed approach can effectively extract high-quality Chinese-Vietnamese parallel sentence pairs based on Chinese-Vietnamese comparable corpus.

    關鍵詞(KeyWords): 句法特征;平行句對抽取;孿生循環神經網絡;漢-越機器翻譯
    syntactic feature;parallel sentence pair extraction;Siamese recurrent neural network;Chinese-Vietnam machine translation

    Abstract:

    Keywords:

    基金項目(Foundation): 國家自然科學基金(61866020);; 云南省教育廳科學研究基金(2019J0674)

    作者(Author): 于志強;高明虎;陳宇星;
    YU Zhi-qiang;GAO Ming-hu;CHEN Yu-xing;Information and Network Center,Yunnan Minzu University;

    Email:

    DOI:

    參考文獻(References):

    擴展功能
    本文信息
    服務與反饋
    本文關鍵詞相關文章
    本文作者相關文章
    中國知網
    分享
    免费资料大全