A survey on machine reading comprehension systems

R Baradaran, R Ghiasi, H Amirkhani - Natural Language Engineering, 2022 - cambridge.org
Machine Reading Comprehension (MRC) is a challenging task and hot topic in Natural
Language Processing. The goal of this field is to develop systems for answering the …

APER: adaptive evidence-driven reasoning network for machine reading comprehension with unanswerable questions

W Peng, Y Hu, J Yu, L Xing, Y Xie - Knowledge-Based Systems, 2021 - Elsevier
Abstract Machine Reading Comprehension with unanswerable questions requires that
systems not only answer questions when possible, but also output an unanswerable …

A survey of methods for revealing and overcoming weaknesses of data-driven Natural Language Understanding

V Schlegel, G Nenadic… - Natural Language …, 2023 - cambridge.org
Recent years have seen a growing number of publications that analyse Natural Language
Understanding (NLU) datasets for superficial cues, whether they undermine the complexity …

A cascaded retrieval-while-reasoning multi-document comprehension framework with incremental attention for medical question answering

J Liu, J Ren, R Bai, Z Zhang, Z Lu - Expert Systems with Applications, 2025 - Elsevier
Abstract Clinical Machine Reading Comprehension (MRC) is challenging due to the need
for medical expertise and comprehensive reasoning chains for diagnosis. This paper …

Improving the robustness of machine reading comprehension via contrastive learning

J Feng, J Sun, D Shao, J Cui - Applied Intelligence, 2023 - Springer
Pre-trained language models achieve high performance on machine reading
comprehension task, but these models lack robustness and are vulnerable to adversarial …

Verb-driven machine reading comprehension with dual-graph neural network

H Zhang, C Jiang - Pattern Recognition Letters, 2023 - Elsevier
Logical reasoning of context is vital for reading comprehension, which requires to explore
the logical relationship through sentence structure. However, previous methods of logical …

[HTML][HTML] Robustness-Eva-MRC: Assessing and analyzing the robustness of neural models in extractive machine reading comprehension

J Fang, H Xu, Z Wu, K Gao, X Che, H Hui - Intelligent Systems with …, 2023 - Elsevier
Deep neural networks, despite their remarkable success in various language understanding
tasks, have been found vulnerable to adversarial attacks and subtle input perturbations …

Continual machine reading comprehension via uncertainty-aware fixed memory and adversarial domain adaptation

Z Wu, H Xu, J Fang, K Gao - arXiv preprint arXiv:2208.05217, 2022 - arxiv.org
Continual Machine Reading Comprehension aims to incrementally learn from a continuous
data stream across time without access the previous seen data, which is crucial for the …

An understanding-oriented robust machine reading comprehension model

F Ren, Y Liu, B Li, S Liu, B Wang, J Wang… - ACM Transactions on …, 2022 - dl.acm.org
Although existing machine reading comprehension models are making rapid progress on
many datasets, they are far from robust. In this article, we propose an understanding …

Integrating a Heterogeneous Graph with Entity-aware Self-attention using Relative Position Labels for Reading Comprehension Model

S Foolad, K Kiani - arXiv preprint arXiv:2307.10443, 2023 - arxiv.org
Despite the significant progress made by transformer models in machine reading
comprehension tasks, they still face limitations in handling complex reasoning tasks due to …