An overview of online fake news: Characterization, detection, and discussion

X Zhang, AA Ghorbani - Information Processing & Management, 2020 - Elsevier
Over the recent years, the growth of online social media has greatly facilitated the way
people communicate with each other. Users of online social media share information …

A comprehensive survey of deep learning for image captioning

MDZ Hossain, F Sohel, MF Shiratuddin… - ACM Computing Surveys …, 2019 - dl.acm.org
Generating a description of an image is called image captioning. Image captioning requires
recognizing the important objects, their attributes, and their relationships in an image. It also …

[PDF][PDF] KLUE: Korean Language Understanding Evaluation

S Park - arxiv preprint arxiv:2105.09680, 2021 - academia.edu
We introduce Korean Language Understanding Evaluation (KLUE) benchmark. KLUE is a
collection of 8 Korean natural language understanding (NLU) tasks, including Topic …

A structural probe for finding syntax in word representations

J Hewitt, CD Manning - Proceedings of the 2019 Conference of …, 2019 - aclanthology.org
Recent work has improved our ability to detect linguistic knowledge in word representations.
However, current methods for detecting syntactic knowledge do not test whether syntax trees …

A deep fusion matching network semantic reasoning model

W Zheng, Y Zhou, S Liu, J Tian, B Yang, L Yin - Applied Sciences, 2022 - mdpi.com
As the vital technology of natural language understanding, sentence representation
reasoning technology mainly focuses on sentence representation methods and reasoning …

Designing and interpreting probes with control tasks

J Hewitt, P Liang - arxiv preprint arxiv:1909.03368, 2019 - arxiv.org
Probes, supervised models trained to predict properties (like parts-of-speech) from
representations (like ELMo), have achieved high accuracy on a range of linguistic tasks. But …

Visualizing and measuring the geometry of BERT

E Reif, A Yuan, M Wattenberg… - Advances in neural …, 2019 - proceedings.neurips.cc
Transformer architectures show significant promise for natural language processing. Given
that a single pretrained model can be fine-tuned to perform well on many different tasks …

This just in: Fake news packs a lot in title, uses simpler, repetitive content in text body, more similar to satire than real news

B Horne, S Adali - Proceedings of the international AAAI conference on …, 2017 - ojs.aaai.org
The problem of fake news has gained a lot of attention as it is claimed to have had a
significant impact on 2016 US Presidential Elections. Fake news is not a new problem and …

Emergent linguistic structure in artificial neural networks trained by self-supervision

CD Manning, K Clark, J Hewitt… - Proceedings of the …, 2020 - National Acad Sciences
This paper explores the knowledge of linguistic structure learned by large artificial neural
networks, trained via self-supervision, whereby the model simply tries to predict a masked …

Universal dependencies v1: A multilingual treebank collection

J Nivre, MC De Marneffe, F Ginter… - Proceedings of the …, 2016 - aclanthology.org
Cross-linguistically consistent annotation is necessary for sound comparative evaluation
and cross-lingual learning experiments. It is also useful for multilingual system development …