Answering multi-hop questions over hybrid factual knowledge from the given
text and table (TextTableQA) is a challenging task. Existing models mainly
adopt a retriever-reader framework, which have several deficiencies, such as
noisy labeling in training retriever, insufficient utilization of heterogeneous
information over text and table, and deficient ability for different reasoning
operations. In this paper, we propose a three-stage TextTableQA framework
S3HQA, which comprises of retriever, selector, and reasoner. We use a retriever
with refinement training to solve the noisy labeling problem. Then, a hybrid
selector considers the linked relationships between heterogeneous data to
select the most relevant factual knowledge. For the final stage, instead of
adapting a reading comprehension module like in previous methods, we employ a
generation-based reasoner to obtain answers. This includes two approaches: a
row-wise generator and an LLM prompting generator~(first time used in this
task). The experimental results demonstrate that our method achieves
competitive results in the few-shot setting. When trained on the full dataset,
our approach outperforms all baseline methods, ranking first on the HybridQA
leaderboard.

在本文中，我们提出了一个三阶段的 TextTableQA 框架 S3HQA，它包括检索器、选择器和推理器。在推理操作方面，我们采用了基于生成模型的推理器，包括一种行生成器和 LLM 提示生成器 (首次在这一任务中使用)。实验结果表明，我们的方法在少样本情况下取得了竞争性成果。当在整个数据集上训练时，我们的方法优于所有基线方法，在 HybridQA 排行榜上排名第一。