本文選題：半監(jiān)督 + 句子級(jí)雙語(yǔ)評(píng)估替補(bǔ)(BLEU)　； 參考：《模式識(shí)別與人工智能》2017年10期

【摘要】：在單語(yǔ)語(yǔ)料的使用上,統(tǒng)計(jì)機(jī)器翻譯可通過(guò)利用語(yǔ)言模型提高性能,而神經(jīng)機(jī)器翻譯很難通過(guò)這種方法有效利用單語(yǔ)語(yǔ)料.針對(duì)此問(wèn)題,文中提出基于句子級(jí)雙語(yǔ)評(píng)估替補(bǔ)(BLEU)指標(biāo)挑選數(shù)據(jù)的半監(jiān)督神經(jīng)網(wǎng)絡(luò)翻譯模型.分別利用統(tǒng)計(jì)機(jī)器翻譯和神經(jīng)機(jī)器翻譯模型對(duì)無(wú)標(biāo)注數(shù)據(jù)生成候選翻譯,然后通過(guò)句子級(jí)BLEU指標(biāo)挑選單語(yǔ)候選翻譯,加入到有標(biāo)注的數(shù)據(jù)集中進(jìn)行半監(jiān)督聯(lián)合訓(xùn)練.實(shí)驗(yàn)表明,文中方法能高效利用無(wú)標(biāo)注的單語(yǔ)語(yǔ)料,在NIST漢英翻譯任務(wù)上,相比僅使用精標(biāo)的有標(biāo)注數(shù)據(jù)單系統(tǒng),文中方法 BLEU值有所提升.
[Abstract]:In the use of monolingual data, statistical machine translation can improve performance by using language models, while neural machine translation is difficult to effectively use monolingual data. To solve this problem, a semi-supervised neural network translation model based on sentence level bilingual evaluation index selection data is proposed in this paper. Statistical machine translation model and neural machine translation model are used to generate candidate translation for untagged data respectively. Then single language candidate translation is selected by sentence level BLEU index and added to annotated data set for semi-supervised joint training. Experiments show that the proposed method can efficiently use unannotated monolingual data, and the BLEU value of the proposed method is improved compared with that of the NIST Chinese-English translation task.
【作者單位】： 中國(guó)科學(xué)技術(shù)大學(xué)語(yǔ)音及語(yǔ)言信息處理國(guó)家工程實(shí)驗(yàn)室;
【基金】：國(guó)家重點(diǎn)研發(fā)計(jì)劃專項(xiàng)項(xiàng)目(No.2016YFB1001303)資助~~
【分類號(hào)】：H085

【相似文獻(xiàn)】

相關(guān)碩士學(xué)位論文 前1條

1 劉芳芳;外事文本機(jī)器翻譯譯文差異的量化研究[D];北京第二外國(guó)語(yǔ)學(xué)院;2017年

，

本文編號(hào)：1926412