QLSC: A Query Latent Semantic Calibrator for Robust Extractive Question Answering
This work addresses robustness issues in extractive question answering for machine reading comprehension systems, representing an incremental improvement.
The paper tackled the challenge of semantically identical but format-variant inputs in extractive question answering by introducing the Query Latent Semantic Calibrator (QLSC) as an auxiliary module, which improved robustness and accuracy in pinpointing answers on robust QA datasets.
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.