1 code implementation • Findings (NAACL) 2022 • Shuo Lei, Xuchao Zhang, Jianfeng He, Fanglan Chen, Chang-Tien Lu
Large-scale multilingual pre-trained language models have achieved remarkable performance in zero-shot cross-lingual tasks.
no code implementations • 27 Mar 2024 • Yanshen Sun, Jianfeng He, Limeng Cui, Shuo Lei, Chang-Tien Lu
Studies highlight the gap in the deceptive power of LLM-generated fake news with and without human assistance, yet the potential of prompting techniques has not been fully explored.
no code implementations • 18 Feb 2024 • Min Zhang, Jianfeng He, Taoran Ji, Chang-Tien Lu
This serves as a reminder to carefully consider sensitivity and confidence in the pursuit of model fairness.
no code implementations • 12 Dec 2023 • Min Zhang, Jianfeng He, Shuo Lei, Murong Yue, Linhang Wang, Chang-Tien Lu
The meaning of complex phrases in natural language is composed of their individual components.
1 code implementation • 4 Dec 2023 • Shengkun Wang, Yangxiao Bai, Taoran Ji, Kaiqun Fu, Linhan Wang, Chang-Tien Lu
We showcase the state-of-the-art performance of our proposed model using a dataset, specifically curated by us, for predicting stock market movements and volatility.
no code implementations • 15 Nov 2023 • Jianfeng He, Linlin Yu, Shuo Lei, Chang-Tien Lu, Feng Chen
Sequential labeling is a task predicting labels for each token in a sequence, such as Named Entity Recognition (NER).
1 code implementation • 28 Oct 2023 • Shengkun Wang, Yangxiao Bai, Kaiqun Fu, Linhan Wang, Chang-Tien Lu, Taoran Ji
For both investors and policymakers, forecasting the stock market is essential as it serves as an indicator of economic well-being.
no code implementations • 29 Sep 2023 • Siji Chen, Yanshen Sun, Peihan Li, Lifeng Zhou, Chang-Tien Lu
However, it has been observed that relying solely on the states of immediate neighbors is insufficient to imitate a centralized control policy.
1 code implementation • 11 Sep 2023 • Linhan Wang, Shuo Lei, Jianfeng He, Shengkun Wang, Min Zhang, Chang-Tien Lu
To tackle these challenges, we propose a Self-Correlation and Cross-Correlation Learning Network for the few-shot remote sensing image semantic segmentation.
1 code implementation • 3 Jun 2023 • Shuo Lei, Xuchao Zhang, Jianfeng He, Fanglan Chen, Chang-Tien Lu
Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieve state-of-the-art performance.
no code implementations • 8 Apr 2023 • Dongjie Wang, Chang-Tien Lu, Yanjie Fu
The two fields of urban planning and artificial intelligence (AI) arose and developed separately.
1 code implementation • 21 Mar 2023 • Yanshen Sun, Kaiqun Fu, Chang-Tien Lu
Therefore, DG-Trans is equipped with dual abilities that extract spatiotemporal dependency and identify anomaly nodes affected by incidents while removing noise introduced by benign nodes.
no code implementations • 24 Oct 2022 • Abdulaziz Alhamadani, Xuchao Zhang, Jianfeng He, Chang-Tien Lu
Yet, Arabic Text Summarization (ATS) is still in its developing stages.
1 code implementation • 4 Aug 2022 • Subhodip Biswas, Fanglan Chen, Zhiqian Chen, Chang-Tien Lu, Naren Ramakrishnan
However, the search operators employed by these population-based methods are mostly designed for real-parameter continuous optimization problems.
1 code implementation • 8 Jun 2022 • Subhodip Biswas, Fanglan Chen, Zhiqian Chen, Chang-Tien Lu, Naren Ramakrishnan
Motivated by these recent developments, we develop a set of similar sampling techniques for designing school boundaries based on the flip proposal.
no code implementations • 26 Dec 2021 • Dongjie Wang, Yanjie Fu, Kunpeng Liu, Fanglan Chen, Pengyang Wang, Chang-Tien Lu
However, three major challenges arise: 1) how to define a quantitative land-use configuration?
1 code implementation • 9 Nov 2021 • Padmaksha Roy, Shailik Sarkar, Subhodip Biswas, Fanglan Chen, Zhiqian Chen, Naren Ramakrishnan, Chang-Tien Lu
The Gaussian Mixture Model layer is implemented to consider the multimodal nature of the real-time data while learning from multiple related time series.
no code implementations • 22 Sep 2021 • Dongjie Wang, Kunpeng Liu, David Mohaisen, Pengyang Wang, Chang-Tien Lu, Yanjie Fu
Texts of spatial entities, on the other hand, provide semantic understanding of latent feature labels, but is insensible to deep SRL models.
1 code implementation • 21 Jul 2021 • Zhiqian Chen, Fanglan Chen, Lei Zhang, Taoran Ji, Kaiqun Fu, Liang Zhao, Feng Chen, Lingfei Wu, Charu Aggarwal, Chang-Tien Lu
Deep learning's performance has been extensively recognized recently.
no code implementations • 16 Oct 2020 • Jianfeng He, Xuchao Zhang, Shuo Lei, Shuhui Wang, Qingming Huang, Chang-Tien Lu, Bei Xiao
Each MEx area has the mask area of the generation as the majority and the boundary of original context as the minority.
no code implementations • 22 Aug 2020 • Dongjie Wang, Yanjie Fu, Pengyang Wang, Bo Huang, Chang-Tien Lu
The objective is then to propose an adversarial learning framework that can automatically generate such tensor for an unplanned area.
no code implementations • 3 Jul 2020 • Shuo Lei, Xuchao Zhang, Jianfeng He, Fanglan Chen, Chang-Tien Lu
Despite the great progress made by deep neural networks in the semantic segmentation task, traditional neural-networkbased methods typically suffer from a shortage of large amounts of pixel-level annotations.
no code implementations • 27 Feb 2020 • Zhiqian Chen, Fanglan Chen, Lei Zhang, Taoran Ji, Kaiqun Fu, Liang Zhao, Feng Chen, Lingfei Wu, Charu Aggarwal, Chang-Tien Lu
Deep learning's success has been widely recognized in a variety of machine learning tasks, including image classification, audio recognition, and natural language processing.
no code implementations • 20 Nov 2019 • Kaiqun Fu, Taoran Ji, Liang Zhao, Chang-Tien Lu
In this paper, we propose a traffic incident duration prediction model that simultaneously predicts the impact of the traffic incidents and identifies the critical groups of temporal features via a multi-task learning framework.
no code implementations • IJCNLP 2019 • Xuchao Zhang, Dheeraj Rajagopal, Michael Gamon, Sujay Kumar Jauhar, Chang-Tien Lu
Thus, in this paper we explore the relationship between comments and edits by defining two novel, related tasks: Comment Ranking and Edit Anchoring.
1 code implementation • NAACL 2019 • Xuchao Zhang, Fanglan Chen, Chang-Tien Lu, Naren Ramakrishnan
The uncertainty measurement of classifiers' predictions is especially important in applications such as medical diagnoses that need to ensure limited human resources can focus on the most uncertain predictions returned by machine learning models.
1 code implementation • 22 May 2019 • Taoran Ji, Zhiqian Chen, Nathan Self, Kaiqun Fu, Chang-Tien Lu, Naren Ramakrishnan
For the problem of patent citations, we observe that forecasting a patent's chain of citations benefits from not only the patent's history itself but also from the historical citations of assignees and inventors associated with that patent.
no code implementations • 14 Feb 2019 • Zhiqian Chen, Gaurav Kolhe, Setareh Rafatirad, Sai Manoj P. D., Houman Homayoun, Liang Zhao, Chang-Tien Lu
Deobfuscation runtime could have a large span ranging from few milliseconds to thousands of years or more, depending on the number and layouts of the ICs and camouflaged gates.
no code implementations • 5 Feb 2019 • Xuchao Zhang, Shuo Lei, Liang Zhao, Arnold P. Boedihardjo, Chang-Tien Lu
The presence of data corruption in user-generated streaming data, such as social media, motivates a new fundamental problem that learns reliable regression coefficient when features are not accessible entirely at one time.
1 code implementation • 30 Aug 2018 • Zhiqian Chen, Feng Chen, Rongjie Lai, Xuchao Zhang, Chang-Tien Lu
RatioanlNet is proposed to integrate rational function and neural networks.
no code implementations • 26 Aug 2018 • Bingsheng Wang, Xuchao Zhang, Chang-Tien Lu, Feng Chen
As the issue of freshwater shortage is increasing daily, it is critical to take effective measures for water conservation.
no code implementations • 6 Jul 2018 • Xuchao Zhang, Liang Zhao, Zhiqian Chen, Chang-Tien Lu
One key issue in SPL is the training process required for each instance weight depends on the other samples and thus cannot easily be run in a distributed manner in a large-scale dataset.
1 code implementation • 5 Dec 2017 • Zhiqian Chen, Chih-Wei Wu, Yen-Cheng Lu, Alexander Lerch, Chang-Tien Lu
FusionGAN is a novel genre fusion framework for music generation that integrates the strengths of generative adversarial networks and dual learning.
no code implementations • 5 Dec 2017 • Zhiqian Chen, Xuchao Zhang, Arnold P. Boedihardjo, Jing Dai, Chang-Tien Lu
Deriving event storylines is an effective summarization method to succinctly organize extensive information, which can significantly alleviate the pain of information overload.
no code implementations • 2 Oct 2017 • Xuchao Zhang, Liang Zhao, Arnold P. Boedihardjo, Chang-Tien Lu
In today's era of big data, robust least-squares regression becomes a more challenging problem when considering the adversarial corruption along with explosive growth of datasets.