Maximum a posteriori decoding, a commonly used method for neural machine
translation (NMT), aims to maximize the estimated posterior probability.
However, high estimated probability does not always lead to high translation
quality. Minimum Bayes Risk (MBR) decoding offers an alternative by seeking
hypotheses with the highest expected utility.
In this work, we show that Quality Estimation (QE) reranking, which uses a QE
model as a reranker, can be viewed as a variant of MBR. Inspired by this, we
propose source-based MBR (sMBR) decoding, a novel approach that utilizes
synthetic sources generated by backward translation as ``support hypotheses''
and a reference-free quality estimation metric as the utility function, marking
the first work to solely use sources in MBR decoding. Experiments show that
sMBR significantly outperforms QE reranking and is competitive with standard
MBR decoding. Furthermore, sMBR calls the utility function fewer times compared
to MBR. Our findings suggest that sMBR is a promising approach for high-quality
NMT decoding.

本研究提出了一种基于源的 MBR 解码方法（sMBR），利用由后向翻译生成的合成源作为 “支持假设”，以及无参考质量估计度量作为效用函数，实现了仅利用源进行 MBR 解码的首次工作。实验证明，sMBR 明显优于 QE 重排并且与标准 MBR 解码相竞争。此外，与 MBR 相比，sMBR 较少调用效用函数的次数。结果表明，sMBR 是一种有潜力提高质量的 NMT 解码方法。

揭示源的威力：基于源的最小贝叶斯风险解码用于神经机器翻译

Unveiling the Power of Source: Source-based Minimum Bayes Risk Decoding  for Neural Machine Translation

We present a deep generative model of bilingual sentence pairs for machine
translation. The model generates source and target sentences jointly from a
shared latent representation and is parameterised by neural networks. We
perform efficient training using amortised variational inference and
reparameterised gradients. Additionally, we discuss the statistical
implications of joint modelling and propose an efficient approximation to
maximum a posteriori decoding for fast test-time predictions. We demonstrate
the effectiveness of our model in three machine translation scenarios:
in-domain training, mixed-domain training, and learning from a mix of
gold-standard and synthetic data. Our experiments show consistently that our
joint formulation outperforms conditional modelling (i.e. standard neural
machine translation) in all such scenarios.

我们提出了一种基于神经网络的双语句子对深度生成模型来进行机器翻译，能够通过共享的潜在表示联合生成源语言句子和目标语言句子，并使用摊余变分推断和重参数化梯度进行高效的训练，可以在领域内、混合领域数据、金标准和合成数据混合学习等各种情况下显示出比条件建模（即标准神经机器翻译）更好的性能。同时，我们讨论了联合建模的统计学意义，并提出了一种高效的近似方法来进行最大后验解码，以便在测试时进行快速预测。

自编码变分神经机器翻译

Auto-Encoding Variational Neural Machine Translation

In this paper, we present a novel algorithm for the maximum a posteriori
decoding (MAPD) of time-homogeneous Hidden Markov Models (HMM), improving the
worst-case running time of the classical Viterbi algorithm by a logarithmic
factor. In our approach, we interpret the Viterbi algorithm as a repeated
computation of matrix-vector $(\max, +)$-multiplications. On time-homogeneous
HMMs, this computation is online: a matrix, known in advance, has to be
multiplied with several vectors revealed one at a time. Our main contribution
is an algorithm solving this version of matrix-vector $(\max,+)$-multiplication
in subquadratic time, by performing a polynomial preprocessing of the matrix.
Employing this fast multiplication algorithm, we solve the MAPD problem in
$O(mn^2/ \log n)$ time for any time-homogeneous HMM of size $n$ and observation
sequence of length $m$, with an extra polynomial preprocessing cost negligible
for $m > n$. To the best of our knowledge, this is the first algorithm for the
MAPD problem requiring subquadratic time per observation, under the only
assumption -- usually verified in practice -- that the transition probability
matrix does not change with time.

本文提出了一种新的算法，通过多项式预处理矩阵来解决时间均匀的 HMM 中 MAPD 问题，并将最坏情况下的运行时间改善了一个对数因子。