| Residential College | false |
| Status | 已發表Published |
| Template-Driven Neural Machine Translation 模板驱动的神经机器翻译 | |
Li，Qiang1; Wong，Fai2 ; Chao，Sam2; Han，Ya Qian1; Xiao，Tong1,3; Zhu，Jing Bo1,3
| |
| 2019-03-01 | |
| Source Publication | Jisuanji Xuebao/Chinese Journal of Computers
 |
| ISSN | 0254-4164 |
| Volume | 42Issue:3Pages:566-581 |
| Abstract | Nowadays, neural machine translation (NMT) has been the most prominent approach to machine translation (MT), due to its simplicity, generality and effectiveness. The principle of neural machine translation is to directly maximize the conditional probabilities of target sentences given source sentences in an end-to-end fashion. One of the most widely used neural machine translation model follows the encoder-decoder framework. It encodes the source sentence using a recurrent neural network (RNN) into a dense context representation, and produces the target translation from the context vector on the decoder. By exploiting the gating and attention mechanisms, neural machine translation models have been shown to surpass the performance of previously dominant statistical machine translation (SMT) on many well-established translation tasks. Recently, researchers have shown an increasing interest in incorporating external lexical translation table and phrase translation table into the neural machine translation, and obtained impressive translation performance. However, in the literature there is less study on incorporating translation templates, which are manually constructed or automatically induced by heuristic algorithm from parallel corpus, into the neural translation model. In this paper, we propose a novel architecture, template driven neural machine translation model, which extends to incorporate the additional translation template into the neural machine translation model. In contrast to the conventional neural machine translation model, on the source side, we use an additional recurrent neural network encoder (template encoder) to encode the additional translation template in parallel to the encoder for the source sentence. In our proposed template driven NMT model, firstly, we propose a gating mechanism, knowledge gate, to balance the information between the source sentence and the additional translation template that is best suited for inducing the source sentence representation. Secondly, to effectively leverage the knowledge representation in predicting the target words, we propose a weighted variant attention mechanism, attention gate, in which a time-dependent gating scalar is adopted to control the ratio of conditional information between the source sentence and the additional translation template. To evaluate the effectiveness of our proposal, we experiment with three kinds of translation templates: 1) head template, where we preserve n words from the leftmost of a sentence and blank out the rest as slot to be predicted and filled by the neural machine translation model; 2) tail template, where the leftmost words are blanked out by keeping the rightmost m words; and 3) normal template, the words are arbitrarily discarded to make slots to be filled by the translation model. Experimental results demonstrate that our proposed model can effectively make use of the additional information from the translation template, and the translation accuracy for the normal translation template with 20% of target words (of the sentence) is up to 93.6% and 95.1% on the Chinese-to-English and English-to-Chinese translation tasks, respectively. When we use 20% of target words as a translation template, we observe significant improvements of 4.2 to 7.2 BLEU scores compared with the baseline systems on the Chinese-to-English and English-to-Chinese translation tasks, respectively. Experiments also show that the translation performance goes up as more context words are considered in the translation template. |
| Keyword | Artificial intelligence Gate unit Natural language processing Neural machine translation Translation template |
| DOI | 10.11897/SP.J.1016.2019.00566 |
| URL | View the original |
| Language | 中文Chinese |
| Scopus ID | 2-s2.0-85068563700 |
| Fulltext Access | |
| Citation statistics | |
| Document Type | Journal article |
| Collection | DEPARTMENT OF COMPUTER AND INFORMATION SCIENCE |
| Affiliation | 1.Natural Language Processing Laboratory,Northeastern University,Shenyang,110000,China 2.Natural Language Processing&Portuguese-Chinese Machine Translation Laboratory,University of Macau,Macau,999078,Macao 3.Shenyang Yatrans Network Technology Co.,Ltd.,Shenyang,110000,China |
| Recommended Citation GB/T 7714 | Li，Qiang,Wong，Fai,Chao，Sam,等. Template-Driven Neural Machine Translation 模板驱动的神经机器翻译[J]. Jisuanji Xuebao/Chinese Journal of Computers, 2019, 42(3), 566-581. |
| APA | Li，Qiang., Wong，Fai., Chao，Sam., Han，Ya Qian., Xiao，Tong., & Zhu，Jing Bo (2019). Template-Driven Neural Machine Translation 模板驱动的神经机器翻译. Jisuanji Xuebao/Chinese Journal of Computers, 42(3), 566-581. |
| MLA | Li，Qiang,et al."Template-Driven Neural Machine Translation 模板驱动的神经机器翻译".Jisuanji Xuebao/Chinese Journal of Computers 42.3(2019):566-581. |
| Files in This Item: | There are no files associated with this item. | |||||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment