论文标题
从组成概括的角度重新访问迭代的反向翻译
Revisiting Iterative Back-Translation from the Perspective of Compositional Generalization
论文作者
论文摘要
人类智能表现出组成的概括（即，理解和产生看不见的组件组合的能力），但是当前的神经SEQ2SEQ模型缺乏这种能力。在本文中，我们重新审视了一种简单而有效的半监督方法，以研究它是否以及如何改善组成概括。在这项工作中：（1）我们首先从经验上表明，迭代反向翻译显着提高了组成概括基准（CFQ和SCAN）的性能。 （2）要了解为什么迭代反向翻译有用，我们仔细检查了性能的增长，并发现迭代反向翻译可以越来越纠正伪并行数据中的错误。 （3）为了进一步鼓励这种机制，我们提出了课程迭代反向翻译，从而更好地提高了伪并行数据的质量，从而进一步提高了性能。
Human intelligence exhibits compositional generalization (i.e., the capacity to understand and produce unseen combinations of seen components), but current neural seq2seq models lack such ability. In this paper, we revisit iterative back-translation, a simple yet effective semi-supervised method, to investigate whether and how it can improve compositional generalization. In this work: (1) We first empirically show that iterative back-translation substantially improves the performance on compositional generalization benchmarks (CFQ and SCAN). (2) To understand why iterative back-translation is useful, we carefully examine the performance gains and find that iterative back-translation can increasingly correct errors in pseudo-parallel data. (3) To further encourage this mechanism, we propose curriculum iterative back-translation, which better improves the quality of pseudo-parallel data, thus further improving the performance.
