Fusion-in-decoder (Fid) (Izacard and Grave, 2020) is a generative question answering (QA) model that leverages passage retrieval with a pre-trained transformer and pushed the state of the art on single-hop QA. However, the complexity of multi-hop QA hinders the effectiveness of the generative QA approach. In this work, we propose a simple generative approach (PathFid) that extends the task beyond just answer generation by explicitly modeling the reasoning process to resolve the answer for multi-hop questions. By linearizing the hierarchical reasoning path of supporting passages, their key sentences, and finally the factoid answer, we cast the problem as a single sequence prediction task. To facilitate complex reasoning with multiple clues, we further extend the unified flat representation of multiple input documents by encoding cross-passage interactions. Our extensive experiments demonstrate that PathFid leads to strong performance gains on two multi-hop QA datasets: HotpotQA and IIRC. Besides the performance gains, PathFid is more interpretable, which in turn yields answers that are more faithfully grounded to the supporting passages and facts compared to the baseline Fid model.
翻译:融合解码器( Fid)( Izacard and Grave, 2020) 是一种基因化解答(QA) 模式,它能以预培训的变压器来利用通道检索,推动单跳QA的先进状态。然而,多跳QA的复杂性妨碍了基因化QA方法的有效性。在此工作中,我们建议一种简单的归正方法(PathFid),它通过明确模拟推理过程来解决多跳问题答案的答案,将任务扩大到公正解析(QA) 。通过将支持通道的等级推理路径、其关键句子以及最终的事实解答线化,我们把问题作为一个单一序列预测任务。为了便利复杂的推理,我们通过对跨过路互动进行编码,进一步扩展多个输入文件的统一统一代表。我们的广泛实验表明,“路径Fid”导致两个多跳的QA数据集(HotpotQA 和 IIRC) 的强大绩效增益。除了业绩增益外,路径Fodefid比较容易解释, 反过来得出更忠实支持基准和基准的答案。