arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1506.00698cs.CL
收藏

基于多任务张量网络的统计机器翻译特征

Statistical Machine Translation Features with Multitask Tensor Networks

Microsoft Research(微软研究院);Raytheon BBN Technologies(雷神BBN技术公司)

Hendra Setiawan, Zhongqiang Huang, Jacob Devlin, Thomas Lamar, Rabih Zbib, Richard Schwartz, John Makhoul

摘要:

我们提出了一个三管齐下的方法来改善统计机器翻译(SMT),建立在最近成功的应用神经网络SMT。首先,我们提出了基于神经网络的新特征来模拟各种非局部翻译现象。其次,我们用张量层来增强神经网络的架构,张量层捕捉网络单元之间重要的高阶交互。第三,我们应用多任务学习来联合估计神经网络参数。我们提出的每一种方法都产生了互补的显著改进。阿拉伯语-英语和中文-英语翻译的整体改进分别为+2.7和+1.8 BLEU点,而这两个点都超过了已经包含神经网络功能的最先进系统。

英文摘要:

We present a three-pronged approach to improving Statistical Machine Translation (SMT), building on recent success in the application of neural networks to SMT. First, we propose new features based on neural networks to model various non-local translation phenomena. Second, we augment the architecture of the neural network with tensor layers that capture important higher-order interaction among the network units. Third, we apply multitask learning to estimate the neural network parameters jointly. Each of our proposed methods results in significant improvements that are complementary. The overall improvement is +2.7 and +1.8 BLEU points for Arabic-English and Chinese-English translation over a state-of-the-art system that already includes neural network features.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑