2000 character limit reached
A Survey on Neural Question Generation: Methods, Applications, and Prospects
Published 28 Feb 2024 in cs.CL and cs.AI | (2402.18267v2)
Abstract: In this survey, we present a detailed examination of the advancements in Neural Question Generation (NQG), a field leveraging neural network techniques to generate relevant questions from diverse inputs like knowledge bases, texts, and images. The survey begins with an overview of NQG's background, encompassing the task's problem formulation, prevalent benchmark datasets, established evaluation metrics, and notable applications. It then methodically classifies NQG approaches into three predominant categories: structured NQG, which utilizes organized data sources, unstructured NQG, focusing on more loosely structured inputs like texts or visual content, and hybrid NQG, drawing on diverse input modalities. This classification is followed by an in-depth analysis of the distinct neural network models tailored for each category, discussing their inherent strengths and potential limitations. The survey culminates with a forward-looking perspective on the trajectory of NQG, identifying emergent research trends and prospective developmental paths. Accompanying this survey is a curated collection of related research papers, datasets and codes, systematically organized on Github, providing an extensive reference for those delving into NQG.
- VQA: visual question answering. In ICCV, 2015.
- Learning to generate questions by learning to recover answer-containing sentences. In ACL, 2021.
- Knowledge-enriched, type-constrained and grammar-guided question generation over knowledge bases. In COLING, 2020.
- Zi Chai and Xiaojun Wan. Learning to ask more: Semi-autoregressive sequential question generation under dual-graph interaction. In ACL, 2020.
- Visual question generation under multi-granularity cross-modal interaction. In MMM, 2023.
- Kgpt: Knowledge-grounded pre-training for data-to-text generation. In EMNLP, 2020.
- Reinforcement learning based graph-to-sequence model for natural question generation. In ICLR, 2020.
- Difficulty-controllable visual question generation. In APWeb-WAIM, 2021.
- Deconfounded visual question generation with causal inference. In ACM MM, 2023.
- Toward subgraph-guided knowledge graph question generation with graph neural networks. TNNLS, 2023.
- Unified language model pre-training for natural language understanding and generation. In NeurIPS, 2019.
- Xinya Du and Claire. Harvesting paragraph-level question-answer pairs from wikipedia. In ACL, 2018.
- Learning to ask: Neural question generation for reading comprehension. In ACL, 2017.
- Zero-shot question generation from knowledge graphs for unseen predicates and entity types. In NAACL, 2018.
- Iterative gnn-based decoder for question generation. In EMNLP, 2021.
- CQG: A simple and effective controlled generation framework for multi-hop question generation. In ACL, 2022.
- Lfkqg: A controlled generation framework with local fine-tuning for question generation over knowledge bases. In COLING, 2022.
- Enhancing human summaries for question-answer generation in education. In BEA@ACL, 2023.
- Beyond I.I.D.: three levels of generalization for question answering on knowledge bases. In WWW, 2021.
- Dsm: Question generation over knowledge base via modeling diverse subgraphs with meta-learner. In EMNLP, 2022.
- Diversifying question generation over knowledge base via external natural questions. arXiv, 2023.
- Jointgt: Graph-text joint representation learning for text generation from knowledge graphs. In ACL, 2021.
- Improving neural question generation using answer separation. In AAAI, 2019.
- Information maximizing visual question generation. In CVPR, 2019.
- Difficulty-controllable multi-hop question generation from knowledge graphs. In ISWC, 2019.
- Cross-lingual training for automatic question generation. In ACL, 2019.
- Denoising seq2seq pre-training for natural language generation, translation, and comprehension. In ACL, 2020.
- Visual question generation as dual task of visual question answering. In CVPR, 2018.
- Improving question generation with to the point context. In EMNLP, 2019.
- Prompting large language models with chain-of-thought for few-shot knowledge base question generation. In EMNLP, 2023.
- Leveraging context for neural question generation in open-domain dialogue systems. In WWW, 2020.
- IVQA: inverse visual question answering. In CVPR, 2018.
- Generating questions for knowledge bases via incorporating diversified contexts and answer-aware loss. In EMNLP, 2019.
- Improving chatgpt prompt for code generation. arXiv, 2023.
- Rquge: Reference-free metric for evaluating question generation by answering the question. In ACL, 2023.
- Generating natural questions about an image. In ACL, 2016.
- Enhancing few-shot text-to-sql capabilities of large language models. arXiv, 2023.
- A human generated machine reading comprehension dataset. In NeurIPS, 2016.
- Reinforced dynamic reasoning for conversational question generation. In ACL, 2019.
- Recent advances in neural question generation. arXiv, 2019.
- Semantic graphs for generating deep questions. In ACL, 2020.
- Unsupervised multi-hop question answering by question generation. In NAACL, 2021.
- Zero-shot fact verification by claim generation. In ACL, 2021.
- Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 2020.
- Squad: 100, 000+ questions for machine comprehension of text. In EMNLP, 2016.
- Generating natural language question-answer pairs from a knowledge graph using a rnn based question generation model. In EACL, 2017.
- A conversational question answering challenge. TACL, 2019.
- Interpretation of natural language rules in conversational machine reading. In EMNLP, 2018.
- Generating factoid questions with recurrent neural networks. In ACL, 2016.
- Directional self-attention network for rnn/cnn-free language understanding. In AAAI, 2018.
- Multi-hop question generation with graph convolutional network. In EMNLP, 2020.
- Neural models for key phrase extraction and question generation. In ACL, 2018.
- Answer-focused and position-aware neural question generation. In EMNLP, 2018.
- Newsqa: A machine comprehension dataset. In ACL, 2017.
- Capturing greater context for question generation. In AAAI, 2020.
- C3VQG: category consistent cyclic visual question generation. In ACM MM Asia, 2020.
- Attention is all you need. In NeurIPS, 2017.
- Multiqg-ti: Towards question generation from multi-modal sources. In ACL, 2023.
- Neural question generation with answer pivot. In AAAI, 2020.
- Deep self-attention distillation for task-agnostic compression of pre-trained transformers. In NeurIPS, 2020.
- Improving question generation with multi-level content planning. In EMNLP, 2023.
- ERNIE-GEN: an enhanced multi-flow pre-training and fine-tuning framework for natural language generation. In IJCAI, 2020.
- Multiple objects-aware visual question generation. In ACM MM, 2021.
- Knowledge-based visual question generation. IEEE Trans. Circuits Syst. Video Technol., 2022.
- Autoqgs: Auto-prompt for low-resource knowledge-based question generation from SPARQL. In CIKM, 2022.
- Radial graph convolutional network for visual question generation. TNNLS, 2020.
- Hotpotqa: A dataset for diverse, explainable multi-hop question answering. In EMNLP, 2018.
- Towards llm-based fact verification on news claims with a hierarchical step-by-step prompting method. In AACL, 2023.
- Meta-cqg: A meta-learning framework for complex question generation over knowledge bases. In COLING, 2022.
- A review on question generation from natural language text. TOIS, 2022.
- Educational question generation of children storybooks. In ACL, 2022.
- An interpretable reasoning network for multi-relation question answering. In COLING, 2018.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.