Devlbert: Learning deconfounded visio-linguistic representations

S Zhang, T Jiang, T Wang, K Kuang, Z Zhao… - Proceedings of the 28th …, 2020‏ - dl.acm.org
In this paper, we propose to investigate the problem of out-of-domain visio-linguistic
pretraining, where the pretraining data distribution differs from that of downstream data on …

Explainable multi-task convolutional neural network framework for electronic petition tag recommendation

Z Yang, J Feng - Electronic Commerce Research and Applications, 2023‏ - Elsevier
Electronic petition (e-petition) is an electronic government (e-government) service that
allows citizens to file petitions to governments via the internet. The complexity of the e …

Interpretable video tag recommendation with multimedia deep learning framework

Z Yang, Z Lin - Internet Research, 2022‏ - emerald.com
Purpose Tags help promote customer engagement on video-sharing platforms. Video tag
recommender systems are artificial intelligence-enabled frameworks that strive for …

An Improved Confounding Effect Model for Software Defect Prediction

Y Yuan, C Li, J Yang - Applied Sciences, 2023‏ - mdpi.com
Software defect prediction technology can effectively improve software quality. Depending
on the code metrics, machine learning models are built to predict potential defects. Some …

Deconfounded and explainable interactive vision-language retrieval of complex scenes

J Wu, T Yu, S Li - Proceedings of the 29th ACM International Conference …, 2021‏ - dl.acm.org
In vision-language retrieval systems, users provide natural language feedback to find target
images. Vision-language explanations in the systems can better guide users to provide …

Bias invariant approaches for improving word embedding fairness

S Liao, R Zhang, B Poblete, V Murdock - Proceedings of the 32nd ACM …, 2023‏ - dl.acm.org
Many public pre-trained word embeddings have been shown to encode different types of
biases. Embeddings are often obtained from training on large pre-existing corpora, and …

基于词频效应控制的神经机器翻译用词多样性增**方法 (Improving Word-level Diversity in Neural Machine Translation by Controlling the Effects of Word Frequency)

X Shi, P Jian, Y Tang, H HUang - Proceedings of the 22nd …, 2023‏ - aclanthology.org
Abstract “通过最大似然估计优化的神经机器翻译(NMT) 容易出现不可最大化的标记或低频词
精度差等问题, 这会导致生成的翻译缺乏词级别的多样性. 词频在训练数据上的不均衡分布是 …