no code implementations • 17 Oct 2023 • Juwu Zheng, Jiangtao Ren
To address these problems, we propose a Multi Self-supervised Pre-fine-tuned Transformer Fusion (MSPTF) network, consisting of two steps: unsupervised pre-fine-tune domain knowledge learning and multi-model fusion target task learning.
no code implementations • 14 Sep 2023 • Juwu Zheng, Jiangtao Ren
Road disease detection is challenging due to the the small proportion of road damage in target region and the diverse background, which introduce lots of domain information. Besides, disease categories have high similarity, makes the detection more difficult.
no code implementations • 13 Sep 2023 • Tengyang Chen, Jiangtao Ren
The Grad-CAM heat map visualization shows that our model can better focus on the local details of the damaged traffic signs.
no code implementations • 13 Sep 2023 • Tengyang Chen, Jiangtao Ren
In addition to using GAN to generate damage with various shapes, we further employ texture synthesis techniques to extract road textures.
no code implementations • COLING 2020 • Qianlong Wang, Jiangtao Ren
Specifically, given an input sentence, our model first predicts the aspect boundary label sequence and sentiment label sequence, then re-predicts the aspect boundary (sentiment) label sequence using the embeddings of the previously predicted sentiment (aspect boundary) label.
1 code implementation • 25 Oct 2020 • Zhaoning Li, Jiangtao Ren
In this paper, we formulate chest abnormal imaging sign extraction as a sequence tagging and matching problem.
1 code implementation • 16 Apr 2019 • Zhaoning Li, Qi Li, Xiaotian Zou, Jiangtao Ren
Causality extraction from natural language texts is a challenging open problem in artificial intelligence.
no code implementations • Proceedings of The 10th Asian Conference on Machine Learning 2018 • Hongli Wang, Jiangtao Ren
This model jointly performs abstractive text summarization and sentiment classification within a hierarchical end-to-end neural framework, in which the sentiment classification layer on top of the summarization layer predicts the sentiment label in the light of the text and the generated summary.