Hybrid question answering (HybridQA) over the financial report contains both textual and tabular data, and requires the model to select the appropriate evidence for the numerical reasoning task. Existing methods based on encoder-decoder framework employ a expression tree-based decoder to solve numerical reasoning problems. However, encoders rely more on Machine Reading Comprehension (MRC) methods, which take table serialization and text splicing as input, damaging the granularity relationship between table and text as well as the spatial structure information of table itself. In order to solve these problems, the paper proposes a Multi-View Graph (MVG) Encoder to take the relations among the granularity into account and capture the relations from multiple view. By utilizing MVGE as a module, we constuct Tabular View, Relation View and Numerical View which aim to retain the original characteristics of the hybrid data. We validate our model on the publicly available table-text hybrid QA benchmark (TAT-QA) and outperform the state-of-the-art model.

翻译：混合问答（HybridQA）涉及金融报告中的文本与表格数据，要求模型为数值推理任务选择合适的证据。现有基于编码器-解码器框架的方法采用表达式树解码器解决数值推理问题。然而，编码器更依赖机器阅读理解（MRC）方法，该方法将表格序列化与文本拼接作为输入，破坏了表格与文本之间的粒度关系以及表格自身的空间结构信息。为解决这些问题，本文提出多视图图（MVG）编码器，以考虑粒度间关系，并从多视角捕获关联。通过将MVGE作为模块，我们构建了表格视图、关系视图与数值视图，旨在保留混合数据的原始特征。我们在公开的表格-文本混合问答基准（TAT-QA）上验证模型，并超越了当前最优模型。