A review on question generation from natural language text

R Zhang, J Guo, L Chen, Y Fan, X Cheng - ACM Transactions on …, 2021 - dl.acm.org
Question generation is an important yet challenging problem in Artificial Intelligence (AI),
which aims to generate natural and relevant questions from various input formats, eg …

Chatgpt asks, blip-2 answers: Automatic questioning towards enriched visual descriptions

D Zhu, J Chen, K Haydarov, X Shen, W Zhang… - arXiv preprint arXiv …, 2023 - arxiv.org
Asking insightful questions is crucial for acquiring knowledge and expanding our
understanding of the world. However, the importance of questioning has been largely …

End-to-end synthetic data generation for domain adaptation of question answering systems

S Shakeri, CN Santos, H Zhu, P Ng, F Nan… - arXiv preprint arXiv …, 2020 - arxiv.org
We propose an end-to-end approach for synthetic QA data generation. Our model comprises
a single transformer-based encoder-decoder network that is trained end-to-end to generate …

Contrastive learning for neural topic model

T Nguyen, AT Luu - Advances in neural information …, 2021 - proceedings.neurips.cc
Recent empirical studies show that adversarial topic models (ATM) can successfully capture
semantic patterns of the document by differentiating a document with another dissimilar …

Improving neural cross-lingual abstractive summarization via employing optimal transport distance for knowledge distillation

TT Nguyen, AT Luu - Proceedings of the AAAI Conference on Artificial …, 2022 - ojs.aaai.org
Current state-of-the-art cross-lingual summarization models employ multi-task learning
paradigm, which works on a shared vocabulary module and relies on the self-attention …

Unsupervised multi-hop question answering by question generation

L Pan, W Chen, W Xiong, MY Kan… - arXiv preprint arXiv …, 2020 - arxiv.org
Obtaining training data for multi-hop question answering (QA) is time-consuming and
resource-intensive. We explore the possibility to train a well-performed multi-hop QA model …

Educational question generation of children storybooks via question type distribution learning and event-centric summarization

Z Zhao, Y Hou, D Wang, M Yu, C Liu, X Ma - arXiv preprint arXiv …, 2022 - arxiv.org
Generating educational questions of fairytales or storybooks is vital for improving children's
literacy ability. However, it is challenging to generate questions that capture the interesting …

Review on neural question generation for education purposes

S Al Faraby, A Adiwijaya, A Romadhony - International Journal of Artificial …, 2024 - Springer
Questioning plays a vital role in education, directing knowledge construction and assessing
students' understanding. However, creating high-level questions requires significant …

Enriching and controlling global semantics for text summarization

T Nguyen, AT Luu, T Lu, T Quan - arXiv preprint arXiv:2109.10616, 2021 - arxiv.org
Recently, Transformer-based models have been proven effective in the abstractive
summarization task by creating fluent and informative summaries. Nevertheless, these …

Synthesize, prompt and transfer: Zero-shot conversational question generation with pre-trained language model

H Zeng, B Wei, J Liu, W Fu - … of the 61st Annual Meeting of the …, 2023 - aclanthology.org
Conversational question generation aims to generate questions that depend on both context
and conversation history. Conventional works utilizing deep learning have shown promising …