论文标题
重新思考标签平滑在多跳的问题答案上
Rethinking Label Smoothing on Multi-hop Question Answering
论文作者
论文摘要
多跳问题答案（MHQA）是相关的重要领域，需要多个推理组件，包括文档检索，支持句子预测和答案跨度提取。在这项工作中，我们分析了限制多跳推理性能的主要因素，并将标签平滑介绍到MHQA任务中。这是为了增强MHQA系统的概括能力，并减轻培训集中的答案跨度和推理路径的过度拟合。我们提出了一种新颖的标签平滑技术F1平滑技术，该技术将不确定性纳入学习过程中，并专门针对机器阅读理解（MRC）任务量身定制。受课程学习原理的启发，我们引入了线性衰变标签平滑算法（LDLA），该算法逐渐降低了整个培训过程中的不确定性。 HOTPOTQA数据集的实验证明了我们方法在增强性能和多跳推理中的性能和概括性方面的有效性，从而在排行榜上取得了新的最新结果。
Multi-Hop Question Answering (MHQA) is a significant area in question answering, requiring multiple reasoning components, including document retrieval, supporting sentence prediction, and answer span extraction. In this work, we analyze the primary factors limiting the performance of multi-hop reasoning and introduce label smoothing into the MHQA task. This is aimed at enhancing the generalization capabilities of MHQA systems and mitigating overfitting of answer spans and reasoning paths in training set. We propose a novel label smoothing technique, F1 Smoothing, which incorporates uncertainty into the learning process and is specifically tailored for Machine Reading Comprehension (MRC) tasks. Inspired by the principles of curriculum learning, we introduce the Linear Decay Label Smoothing Algorithm (LDLA), which progressively reduces uncertainty throughout the training process. Experiment on the HotpotQA dataset demonstrates the effectiveness of our methods in enhancing performance and generalizability in multi-hop reasoning, achieving new state-of-the-art results on the leaderboard.
