在本文中,我们提出了一个混合神经网络增强基于物理的建模(APBM)框架,用于贝叶斯非线性潜在空间估计。提出的APBM策略允许在新的操作条件发挥作用时进行模型适应,或者基于物理的模型不足(或不完整)无法正确描述潜在现象。APBM的优点和我们的估计程序是维持估计状态的物理解释性的能力。此外,我们提出了一种约束过滤方法,以控制对整个模型的神经网络贡献。我们还利用假定的密度滤波技术和立方体集成规则,以提出灵活的估计策略,该策略可以轻松处理非线性模型和高维度的潜在空间。最后,我们通过分别利用非线性和不完整的测量和加速模型来利用目标跟踪方案来证明我们的方法论的功效。
translated by 谷歌翻译
We present Charles University submissions to the WMT22 General Translation Shared Task on Czech-Ukrainian and Ukrainian-Czech machine translation. We present two constrained submissions based on block back-translation and tagged back-translation and experiment with rule-based romanization of Ukrainian. Our results show that the romanization only has a minor effect on the translation quality. Further, we describe Charles Translator, a system that was developed in March 2022 as a response to the migration from Ukraine to the Czech Republic. Compared to our constrained systems, it did not use the romanization and used some proprietary data sources.
translated by 谷歌翻译
We present a non-autoregressive system submission to the WMT 22 Efficient Translation Shared Task. Our system was used by Helcl et al. (2022) in an attempt to provide fair comparison between non-autoregressive and autoregressive models. This submission is an effort to establish solid baselines along with sound evaluation methodology, particularly in terms of measuring the decoding speed. The model itself is a 12-layer Transformer model trained with connectionist temporal classification on knowledge-distilled dataset by a strong autoregressive teacher model.
translated by 谷歌翻译
我们解决了神经机翻译中的两个域适应问题。首先,我们希望达到领域的稳健性,即培训数据的域名的良好质量,以及培训数据中的域名不间断。其次,我们希望我们的系统是Adaptive的,即,可以使用只有数百个域的平行句子来实现Finetune系统。在本文中,我们介绍了两个先前方法的新组合,文字自适应建模,解决了域的鲁棒性和荟萃学习,解决了域适应性,并且我们呈现了显示我们新组合改善这些属性的经验结果。
translated by 谷歌翻译
我们提出了一项调查,涵盖了低资源机器翻译中的最新技术。目前,世界上有大约7000种语言,几乎所有语言对都缺乏培训机器翻译模型的重要资源。对研究挑战在很少翻译的训练数据时,对研究有用翻译模型的挑战越来越富有兴趣。我们提出了这一局部领域的高级摘要,并提供了最佳实践的概述。
translated by 谷歌翻译