Hybrid tabular-textual question answering (QA) requires reasoning from heterogeneous information, and the types of reasoning are mainly divided into numerical reasoning and span extraction. Current numerical reasoning methods autoregressively decode program sequences, and each decoding step produces either an operator or an operand. However, the step-by-step decoding suffers from exposure bias, and the accuracy of program generation drops sharply as the decoding steps unfold due to error propagation. In this paper, we propose a non-autoregressive program generation framework, which independently generates complete program tuples containing both operators and operands, can address the error propagation issue while significantly boosting the speed of program generation. Experiments on the ConvFinQA and MultiHiertt datasets show that our non-autoregressive program generation method can bring about substantial improvements over the strong FinQANet (+5.06 Exe Acc and +4.80 Prog Acc points) and MT2Net (+7.97 EM and +6.38 F1 points) baselines, establishing the new state-of-the-art performance, while being much faster (21x) in program generation. Finally, with increasing numbers of numerical reasoning steps the performance drop of our method is significantly smaller than that of the baselines. Our code will be publicly available soon.

翻译：混合表格-文本问答需要从异构信息中进行推理，其推理类型主要分为数值推理和跨度抽取两类。当前数值推理方法采用自回归方式解码程序序列，每个解码步骤生成一个运算符或操作数。然而，逐步解码存在曝光偏差问题，且随着解码步骤推进，错误传播导致程序生成准确率急剧下降。本文提出一种非自回归程序生成框架，该框架可独立生成包含运算符和操作数的完整程序元组，在显著提升程序生成速度的同时有效解决错误传播问题。在ConvFinQA和MultiHiertt数据集上的实验表明，我们的非自回归程序生成方法相较于强基线模型FinQANet（执行准确率+5.06，程序准确率+4.80个百分点）和MT2Net（精确匹配+7.97，F1值+6.38个百分点）带来显著提升，在程序生成速度提升21倍的基础上创下新的最优性能记录。此外，随着数值推理步骤增加，本方法性能下降幅度显著小于基线模型。代码即将公开。