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.

本研究通过迭代回译一种简单而有效的半监督方法，证实其对于复合泛化的基准数据（CFQ 和 SCAN）的性能显著提高，并为理解这一机制提出了课程迭代回译，进一步提高伪并行数据的质量，进一步改善性能。

从组合概括的角度重新审视迭代回译

Revisiting Iterative Back-Translation from the Perspective of  Compositional Generalization

Recent years have seen great success in the use of neural seq2seq models on
the text-to-SQL task. However, little work has paid attention to how these
models generalize to realistic unseen data, which naturally raises a question:
does this impressive performance signify a perfect generalization model, or are
there still some limitations?
In this paper, we first diagnose the bottleneck of text-to-SQL task by
providing a new testbed, in which we observe that existing models present poor
generalization ability on rarely-seen data. The above analysis encourages us to
design a simple but effective auxiliary task, which serves as a supportive
model as well as a regularization term to the generation task to increase the
models generalization. Experimentally, We evaluate our models on a large
text-to-SQL dataset WikiSQL. Compared to a strong baseline coarse-to-fine
model, our models improve over the baseline by more than 3% absolute in
accuracy on the whole dataset. More interestingly, on a zero-shot subset test
of WikiSQL, our models achieve 5% absolute accuracy gain over the baseline,
clearly demonstrating its superior generalizability.

研究了神经序列到序列模型在自然生成的 SQL 任务中的泛化能力问题，并通过构建辅助任务并在 WikiSQL 数据集上的实验中证明其有效性。

辅助任务零样本文本到 SQL 学习

Zero-shot Text-to-SQL Learning with Auxiliary Task

Neural state-of-the-art sequence-to-sequence (seq2seq) models often do not
perform well for small training sets. We address paradigm completion, the
morphological task of, given a partial paradigm, generating all missing forms.
We propose two new methods for the minimal-resource setting: (i) Paradigm
transduction: Since we assume only few paradigms available for training, neural
seq2seq models are able to capture relationships between paradigm cells, but
are tied to the idiosyncracies of the training set. Paradigm transduction
mitigates this problem by exploiting the input subset of inflected forms at
test time. (ii) Source selection with high precision (SHIP): Multi-source
models which learn to automatically select one or multiple sources to predict a
target inflection do not perform well in the minimal-resource setting. SHIP is
an alternative to identify a reliable source if training data is limited. On a
52-language benchmark dataset, we outperform the previous state of the art by
up to 9.71% absolute accuracy.

在小型训练集下，我们针对 neural seq2seq models 在 paradigm completion 的应用中性能低下提出了两种新方法：1. Paradigm transduction， 2. Source selection with high precision (SHIP)， 在 52 种语言的基准数据集上，我们相比之前的技术水平在最高达 9.71% 的绝对准确率上实现了优异表现。