In this paper, we describe two CU Boulder submissions to SIGMORPHON 2020 Task 1 on multilingual grapheme-to-phoneme conversion (G2P). Inspired by the high performance of a standard transformer model (Vaswani et al., 2017) on the task, we improve over this approach by adding two modifications: (ⅰ) Instead of training exclusively on G2P, we additionally create examples for the opposite direction, phoneme-to-grapheme conversion (P2G). We then perform multi-task training on both tasks, (ⅱ) We produce ensembles of our models via majority voting. Our approaches, though being conceptually simple, result in systems that place 6th and 8th amongst 23 submitted systems, and obtain the best results out of all systems on Lithuanian and Modern Greek, respectively.
展开▼
机译：在本文中，我们描述了两个CU Boulder提交给SIGMORPHON 2020任务1的多语言音素到音素转换（G2P）。受标准变压器模型（Vaswani et al。，2017）高性能的启发，我们通过添加以下两种改进对这种方法进行了改进：（ⅰ）除了专门针对G2P进行培训之外，我们还针对相反的方向创建了示例，音素到字素转换（P2G）。然后，我们对这两个任务都执行多任务训练，（ⅱ）我们通过多数表决产生模型的集合。我们的方法尽管从概念上讲很简单，但其系统在提交的23个系统中排名第六和第八，并分别在立陶宛语和现代希腊语的所有系统中获得最佳结果。
展开▼
