Cross-modal memory networks for radiology report generation

Z Chen, Y Shen, Y Song, X Wan - arxiv preprint arxiv:2204.13258, 2022 - arxiv.org
Medical imaging plays a significant role in clinical practice of medical diagnosis, where the
text reports of the images are essential in understanding them and facilitating later …

[HTML][HTML] GECRAN: Graph embedding based convolutional recurrent attention network for traffic flow prediction

JQ Yan, L Zhang, Y Gao, BT Qu - Expert Systems with Applications, 2024 - Elsevier
Traffic flow prediction has become increasingly important with the rapid development of
Intelligent Transportation Systems (ITS) in recent years. Due to the accurate representation …

Semeval-2022 task 11: Multilingual complex named entity recognition (multiconer)

S Malmasi, A Fang, B Fetahu, S Kar… - Proceedings of the …, 2022 - aclanthology.org
We present the findings of SemEval-2022 Task 11 on Multilingual Complex Named Entity
Recognition MULTICONER. Divided into 13 tracks, the task focused on methods to identify …

Lexicon enhanced Chinese sequence labeling using BERT adapter

W Liu, X Fu, Y Zhang, W **ao - arxiv preprint arxiv:2105.07148, 2021 - arxiv.org
Lexicon information and pre-trained models, such as BERT, have been combined to explore
Chinese sequence labelling tasks due to their respective strengths. However, existing …

Wukong: A 100 million large-scale chinese cross-modal pre-training benchmark

J Gu, X Meng, G Lu, L Hou, N Minzhe… - Advances in …, 2022 - proceedings.neurips.cc
Abstract Vision-Language Pre-training (VLP) models have shown remarkable performance
on various downstream tasks. Their success heavily relies on the scale of pre-trained cross …

Weak supervision for fake news detection via reinforcement learning

Y Wang, W Yang, F Ma, J Xu, B Zhong, Q Deng… - Proceedings of the AAAI …, 2020 - aaai.org
Today social media has become the primary source for news. Via social media platforms,
fake news travel at unprecedented speeds, reach global audiences and put users and …

Graph-based text representation and matching: A review of the state of the art and future challenges

AH Osman, OM Barukub - IEEE Access, 2020 - ieeexplore.ieee.org
Graph-based text representation is one of the important preprocessing steps in data and text
mining, Natural Language Processing (NLP), and information retrieval approaches. The …

Is college education less necessary with AI? Evidence from firm-level labor structure changes

M Xue, X Cao, X Feng, B Gu… - Journal of Management …, 2022 - Taylor & Francis
As a general-purpose technology, artificial intelligence (AI) is expected to transform almost
all industries and aspects of our society. Thus, it is important to understand the potential …

Leveraging distribution alignment via stein path for cross-domain cold-start recommendation

W Liu, J Su, C Chen, X Zheng - Advances in Neural …, 2021 - proceedings.neurips.cc
Abstract Cross-Domain Recommendation (CDR) has been popularly studied to utilize
different domain knowledge to solve the cold-start problem in recommender systems. In this …

ZEN: Pre-training Chinese text encoder enhanced by n-gram representations

S Diao, J Bai, Y Song, T Zhang, Y Wang - arxiv preprint arxiv:1911.00720, 2019 - arxiv.org
The pre-training of text encoders normally processes text as a sequence of tokens
corresponding to small text units, such as word pieces in English and characters in Chinese …