QLSC: A Query Latent Semantic Calibrator for Robust Extractive Question Answering
Lists
Only you see this
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 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.
BibTeX
@inproceedings{ouyang2024qlsc,
author = {Sheng Ouyang and Jianzong Wang and Yong Zhang and Zhitao Li and Ziqi Liang and Xulong Zhang and Ning Cheng and Jing Xiao},
title = {{QLSC: A Query Latent Semantic Calibrator for Robust Extractive Question Answering}},
booktitle = {IJCNN},
year = {2024},
doi = {10.1109/ijcnn60899.2024.10651462},
}| Improving Lexical Embeddings for Robust Question Answering | arXiv · 2022 |
| Towards Robust Extractive Question Answering Models: Rethinking the Training Methodology | EMNLP · 2024 |
| Improving the Robustness of Question Answering Systems to Question Paraphrasing | ACL · 2019 |
| An Understanding-oriented Robust Machine Reading Comprehension Model | ACM Trans. Asian low Resour. Lang. Inf. Process · 2023 |
| Knowing More About Questions Can Help: Improving Calibration in Question Answering | arXiv · 2021 |
| Learning Invariant Representation Improves Robustness for MRC Models | EMNLP · 2022 |