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 …
We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers. We show how to train the model using a combination …
Question Generation (QG) is fundamentally a simple syntactic transformation; however, many aspects of semantics influence what questions are good to form. We implement this …
A Hadifar, SK Bitew, J Deleu, C Develder… - IEEE …, 2023 - ieeexplore.ieee.org
Natural language processing technology has made significant progress in recent years, fuelled by increasingly powerful general language models. This has also inspired a sizeable …
M Flor, B Riordan - Proceedings of the thirteenth workshop on …, 2018 - aclanthology.org
We present a novel rule-based system for automatic generation of factual questions from sentences, using semantic role labeling (SRL) as the main form of text analysis. The system …
P Khullar, K Rachna, M Hase… - Proceedings of ACL …, 2018 - aclanthology.org
This paper presents a system that automatically generates multiple, natural language questions using relative pronouns and relative adverbs from complex English sentences …
G Danon, M Last - arXiv preprint arXiv:1712.09827, 2017 - arxiv.org
Factoid questions are questions that require short fact-based answers. Automatic generation (AQG) of factoid questions from a given text can contribute to educational activities …
K Mazidi, P Tarau - Proceedings of the 9th International Natural …, 2016 - aclanthology.org
We present a fresh approach to automatic question generation that significantly increases the percentage of acceptable questions compared to prior state-of-the-art systems. In our …
S Vajjala, I Lučić - Proceedings of the Fourteenth Workshop on …, 2019 - aclanthology.org
Automatic readability assessment aims to ensure that readers read texts that they can comprehend. However, computational models are typically trained on texts created from the …