Chart question answering (CQA) is a task used for assessing chart
comprehension, which is fundamentally different from understanding natural
images. CQA requires analyzing the relationships between the textual and the
visual components of a chart, in order to answer general questions or infer
numerical values. Most existing CQA datasets and models are based on
simplifying assumptions that often enable surpassing human performance. In this
work, we address this outcome and propose a new model that jointly learns
classification and regression. Our language-vision setup uses co-attention
transformers to capture the complex real-world interactions between the
question and the textual elements. We validate our design with extensive
experiments on the realistic PlotQA dataset, outperforming previous approaches
by a large margin, while showing competitive performance on FigureQA. Our model
is particularly well suited for realistic questions with out-of-vocabulary
answers that require regression.

本文针对图表理解任务的挑战，提出了一种新型的图表问答模型。我们提出的联合分类与回归模型使用了共现注意力变换器，在处理文本语言和视觉元素的复杂互动时表现出色。在经过广泛的实验验证后，我们的模型在真实场景下的 PlotQA 数据集上表现出卓越的性能，也在 FigureQA 数据集上表现出竞争性的结果。此外，我们的模型特别适用于需要回归的非词汇库答案的实际问题。