CAR: conceptualization-augmented reasoner for zero-shot commonsense question answering

W Wang, T Fang, W Ding, B Xu, X Liu, Y Song… - arXiv preprint arXiv …, 2023 - arxiv.org
The task of zero-shot commonsense question answering evaluates models on their capacity
to reason about general scenarios beyond those presented in specific datasets. Existing …

Peacok: Persona commonsense knowledge for consistent and engaging narratives

S Gao, B Borges, S Oh, D Bayazit, S Kanno… - arXiv preprint arXiv …, 2023 - arxiv.org
Sustaining coherent and engaging narratives requires dialogue or storytelling agents to
understand how the personas of speakers or listeners ground the narrative. Specifically …

DiffuCOMET: Contextual Commonsense Knowledge Diffusion

S Gao, M Ismayilzada, M Zhao, H Wakaki… - arXiv preprint arXiv …, 2024 - arxiv.org
Inferring contextually-relevant and diverse commonsense to understand narratives remains
challenging for knowledge models. In this work, we develop a series of knowledge models …

Profiling the barriers to the spreading of news using news headlines

A Sittar, D Mladenić, M Grobelnik - Frontiers in Artificial Intelligence, 2023 - frontiersin.org
News headlines can be a good data source for detecting the barriers to the spreading of
news in news media, which can be useful in many real-world applications. In this study, we …

Profiling the news spreading barriers using news headlines

A Sittar, D Mladenic, M Grobelnik - arXiv preprint arXiv:2304.11088, 2023 - arxiv.org
News headlines can be a good data source for detecting the news spreading barriers in
news media, which may be useful in many real-world applications. In this paper, we utilize …

High-quality distractor generation framework for English reading comprehension

Z Guo, H Wang, G Guo - 2023 5th International Academic …, 2023 - ieeexplore.ieee.org
Distractors are widely used in tasks such as reading comprehension and subject education.
Generating high-quality distractors automatically poses a challenging task. Existing …