Neural machine reading comprehension: Methods and trends

S Liu, X Zhang, S Zhang, H Wang, W Zhang - Applied Sciences, 2019 - mdpi.com
Machine reading comprehension (MRC), which requires a machine to answer questions
based on a given context, has attracted increasing attention with the incorporation of various …

Semantics-aware BERT for language understanding

Z Zhang, Y Wu, H Zhao, Z Li, S Zhang, X Zhou… - Proceedings of the …, 2020 - ojs.aaai.org
The latest work on language representations carefully integrates contextualized features into
language model training, which enables a series of success especially in various machine …

[PDF][PDF] Bert: Pre-training of deep bidirectional transformers for language understanding

JDMWC Kenton, LK Toutanova - Proceedings of naacL-HLT, 2019 - eva.fing.edu.uy
We introduce a new language representation model called BERT, which stands for
Bidirectional Encoder Representations from Transformers. Unlike recent language …

Text compression-aided transformer encoding

Z Li, Z Zhang, H Zhao, R Wang, K Chen… - … on Pattern Analysis …, 2021 - ieeexplore.ieee.org
Text encoding is one of the most important steps in Natural Language Processing (NLP). It
has been done well by the self-attention mechanism in the current state-of-the-art …

Multi-style generative reading comprehension

K Nishida, I Saito, K Nishida, K Shinoda… - arXiv preprint arXiv …, 2019 - arxiv.org
This study tackles generative reading comprehension (RC), which consists of answering
questions based on textual evidence and natural language generation (NLG). We propose a …

Answer uncertainty and unanswerability in multiple-choice machine reading comprehension

V Raina, M Gales - Findings of the Association for Computational …, 2022 - aclanthology.org
Abstract Machine reading comprehension (MRC) has drawn a lot of attention as an
approach for assessing the ability of systems to understand natural language. Usually …

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 novel multi-layer feature fusion-based BERT-CNN for sentence representation learning and classification

KH Alyoubi, FS Alotaibi, A Kumar, V Gupta… - Robotic Intelligence …, 2023 - emerald.com
Purpose The purpose of this paper is to describe a new approach to sentence
representation learning leading to text classification using Bidirectional Encoder …

A question answering-based framework for one-step event argument extraction

Y Zhang, G Xu, Y Wang, D Lin, F Li, C Wu… - Ieee …, 2020 - ieeexplore.ieee.org
Event argument extraction, which aims to identify arguments of specific events and label
their roles, is a challenging subtask of event extraction. Previous approaches solve this …

Improving machine reading comprehension via adversarial training

Z Yang, Y Cui, W Che, T Liu, S Wang, G Hu - arXiv preprint arXiv …, 2019 - arxiv.org
Adversarial training (AT) as a regularization method has proved its effectiveness in various
tasks, such as image classification and text classification. Though there are successful …