Rethinking Label Smoothing on Multi-hop Question Answering

• URL: http://arxiv.org/abs/2212.09512v3
• Date: Wed, 13 Dec 2023 16:27:16 GMT
• Title: Rethinking Label Smoothing on Multi-hop Question Answering
• Authors: Zhangyue Yin, Yuxin Wang, Xiannian Hu, Yiguang Wu, Hang Yan, Xinyu Zhang, Zhao Cao, Xuanjing Huang, Xipeng Qiu
• Abstract summary: Multi-Hop Question Answering (MHQA) is a significant area in question answering. In this work, we analyze the primary factors limiting the performance of multi-hop reasoning. We propose a novel label smoothing technique, F1 Smoothing, which incorporates uncertainty into the learning process.
• Score: 87.68071401870283
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.