QLSC：一种用于鲁棒抽取式问答的查询潜在语义校准器
QLSC: A Query Latent Semantic Calibrator for Robust Extractive Question Answering
AI总结：
本文提出查询潜在语义校准器QLSC，通过缩放策略捕获查询潜在语义中心特征，并利用注意力机制融合查询与段落嵌入，从而提升抽取式问答模型对格式变化但语义相同输入的鲁棒性和答案定位准确性。
摘要：
机器阅读理解（MRC）中的抽取式问答（EQA）常常面临处理语义相同但格式变化的输入的挑战。我们的工作引入了一种新方法，称为“查询潜在语义校准器（QLSC）”，设计为现有MRC模型的辅助模块。我们提出了一种独特的缩放策略来捕获查询的潜在语义中心特征。然后，这些特征通过注意力机制无缝集成到传统的查询和段落嵌入中。通过加深对语义查询-段落关系的理解，我们的方法降低了对文本格式变化的敏感性，并提升了模型准确定位答案的能力。在鲁棒问答数据集上的实验结果证实，我们的方法能够有效处理格式变化但语义相同的查询，突显了所提方法的有效性和适应性。
英文摘要：
Extractive Question Answering (EQA) in Machine Reading Comprehension (MRC) often faces the challenge of dealing with semantically identical but format-variant inputs. Our work introduces a novel approach, called the ``Query Latent Semantic Calibrator (QLSC)'', designed as an auxiliary module for existing MRC models. We propose a unique scaling strategy to capture latent semantic center features of queries. These features are then seamlessly integrated into traditional query and passage embeddings using an attention mechanism. By deepening the comprehension of the semantic queries-passage relationship, our approach diminishes sensitivity to variations in text format and boosts the model's capability in pinpointing accurate answers. Experimental results on robust Question-Answer datasets confirm that our approach effectively handles format-variant but semantically identical queries, highlighting the effectiveness and adaptability of our proposed method.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
