QLSC: A Query Latent Semantic Calibrator for Robust Extractive Question Answering

arXiv:2404.19316v1 Announce Type: new
Abstract: 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 …

abstract arxiv challenge cs.cl format inputs machine novel query question question answering reading robust semantic type work