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.

翻译：抽取式问答（EQA）作为机器阅读理解（MRC）中的一项任务，常面临处理语义相同但格式变异的输入挑战。本文提出一种名为"查询潜在语义校准器（QLSC）"的新方法，旨在作为现有MRC模型的辅助模块。我们提出一种独特的缩放策略，用于捕获查询的潜在语义中心特征。随后，通过注意力机制将这些特征无缝集成到传统的查询与段落嵌入中。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，并提升了模型精确定位答案的能力。在鲁棒性问答数据集上的实验结果证实，该方法能够有效处理格式变异但语义相同的查询，凸显了所提方法的有效性与适应性。