Generative language models for paragraph-level question generation

A Ushio, F Alva-Manchego… - arXiv preprint arXiv …, 2022 - arxiv.org
Powerful generative models have led to recent progress in question generation (QG).
However, it is difficult to measure advances in QG research since there are no standardized …

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 …

Reinforcement learning-driven deep question generation with rich semantics

M Guan, SK Mondal, HN Dai, H Bao - Information Processing & …, 2023 - Elsevier
Deep question generation (DQG) refers to generating a complex question from different
sentences in context. Existing methods mainly focus on enhancing information extraction …

Selecting better samples from pre-trained LLMs: A case study on question generation

X Yuan, T Wang, YH Wang, E Fine… - arXiv preprint arXiv …, 2022 - arxiv.org
Large Language Models (LLMs) have in recent years demonstrated impressive prowess in
natural language generation. A common practice to improve generation diversity is to …

Peek across: Improving multi-document modeling via cross-document question-answering

A Caciularu, ME Peters, J Goldberger, I Dagan… - arXiv preprint arXiv …, 2023 - arxiv.org
The integration of multi-document pre-training objectives into language models has resulted
in remarkable improvements in multi-document downstream tasks. In this work, we propose …

A practical toolkit for multilingual question and answer generation

A Ushio, F Alva-Manchego… - arXiv preprint arXiv …, 2023 - arxiv.org
Generating questions along with associated answers from a text has applications in several
domains, such as creating reading comprehension tests for students, or improving document …

Question generation and answering for exploring digital humanities collections

F Bechet, E Antoine, J Auguste… - Proceedings of the …, 2022 - aclanthology.org
This paper introduces the question answering paradigm as a way to explore digitized
archive collections for Social Science studies. In particular, we are interested in evaluating …

" What makes a question inquisitive?" A Study on Type-Controlled Inquisitive Question Generation

L Gao, D Ghosh, K Gimpel - arXiv preprint arXiv:2205.08056, 2022 - arxiv.org
We propose a type-controlled framework for inquisitive question generation. We annotate an
inquisitive question dataset with question types, train question type classifiers, and finetune …

Promptly Predicting Structures: The Return of Inference

M Mehta, V Pyatkin, V Srikumar - arXiv preprint arXiv:2401.06877, 2024 - arxiv.org
Prompt-based methods have been used extensively across NLP to build zero-and few-shot
label predictors. Many NLP tasks are naturally structured: that is, their outputs consist of …

DiffQG: Generating questions to summarize factual changes

JR Cole, P Jain, JM Eisenschlos, MJQ Zhang… - arXiv preprint arXiv …, 2023 - arxiv.org
Identifying the difference between two versions of the same article is useful to update
knowledge bases and to understand how articles evolve. Paired texts occur naturally in …