no code implementations • 30 Jul 2016 • Chenguang Wang, Yangqiu Song, Dan Roth, Ming Zhang, Jiawei Han
We provide three ways to specify the world knowledge to domains by resolving the ambiguity of the entities and their types, and represent the data with world knowledge as a heterogeneous information network.
no code implementations • EMNLP 2017 • Chenguang Wang, Alan Akbik, Laura Chiticariu, Yunyao Li, Fei Xia, Anbang Xu
Crowdsourcing has proven to be an effective method for generating labeled data for a range of NLP tasks.
1 code implementation • arXiv 2019 • Chenguang Wang, Mu Li, Alexander J. Smola
In this paper, we explore effective Transformer architectures for language model, including adding additional LSTM layers to better capture the sequential context while still keeping the computation efficient.
Ranked #2 on Language Modelling on Penn Treebank (Word Level) (using extra training data)
4 code implementations • 9 Jul 2019 • Jian Guo, He He, Tong He, Leonard Lausen, Mu Li, Haibin Lin, Xingjian Shi, Chenguang Wang, Junyuan Xie, Sheng Zha, Aston Zhang, Hang Zhang, Zhi Zhang, Zhongyue Zhang, Shuai Zheng, Yi Zhu
We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating).
no code implementations • COLING 2020 • Yichun Yin, Chenguang Wang, Ming Zhang
Dependency context-based word embedding jointly learns the representations of word and dependency context, and has been proved effective in aspect term extraction.
no code implementations • 2 Dec 2019 • Chenguang Wang
It is impractical for users to provide the meta-path(s) to support the large scale inference, and biased examples will result in incorrect meta-path based inference, thus limit the power of the meta-path.
1 code implementation • 14 Feb 2020 • Chenguang Wang, Zihao Ye, Aston Zhang, Zheng Zhang, Alexander J. Smola
Transformer has been widely used thanks to its ability to capture sequence information in an efficient way.
no code implementations • 4 Mar 2020 • Chenguang Wang, Simon Tindemans, Kaikai Pan, Peter Palensky
State estimation is of considerable significance for the power system operation and control.
no code implementations • 14 May 2020 • Chenguang Wang, Kaikai Pan, Simon Tindemans, Peter Palensky
The security of energy supply in a power grid critically depends on the ability to accurately estimate the state of the system.
2 code implementations • 22 Oct 2020 • Chenguang Wang, Xiao Liu, Dawn Song
This paper shows how to construct knowledge graphs (KGs) from pre-trained language models (e. g., BERT, GPT-2/3), without human supervision.
no code implementations • 24 Mar 2021 • Chenguang Wang, Ziwen Liu
For this purpose, we propose a universal framework to generate subgraphs in an auto-regressive way and then using these subgraphs to guide the learning of graph representation by Graph Neural Networks.
1 code implementation • EMNLP 2021 • Chenguang Wang, Xiao Liu, Zui Chen, Haoyun Hong, Jie Tang, Dawn Song
We cast a suite of information extraction tasks into a text-to-triple translation framework.
Ranked #1 on Open Information Extraction on OIE2016 (using extra training data)
1 code implementation • 21 Oct 2021 • Chenguang Wang, Ensieh Sharifnia, Zhi Gao, Simon H. Tindemans, Peter Palensky
In this paper, a multivariate load state generating model on the basis of a conditional variational autoencoder (CVAE) neural network is proposed.
no code implementations • 28 Oct 2021 • Chenguang Wang, Yaodong Yang, Oliver Slumbers, Congying Han, Tiande Guo, Haifeng Zhang, Jun Wang
In this paper, we introduce a two-player zero-sum framework between a trainable \emph{Solver} and a \emph{Data Generator} to improve the generalization ability of deep learning-based solvers for Traveling Salesman Problem (TSP).
1 code implementation • 5 Dec 2021 • Xuanli He, Qiongkai Xu, Lingjuan Lyu, Fangzhao Wu, Chenguang Wang
Nowadays, due to the breakthrough in natural language generation (NLG), including machine translation, document summarization, image captioning, etc NLG models have been encapsulated in cloud APIs to serve over half a billion people worldwide and process over one hundred billion word generations per day.
1 code implementation • Findings (ACL) 2022 • Chenguang Wang, Xiao Liu, Zui Chen, Haoyun Hong, Jie Tang, Dawn Song
We introduce a method for improving the structural understanding abilities of language models.
Ranked #1 on Open Information Extraction on Penn Treebank
no code implementations • 8 Sep 2022 • Chenguang Wang, Simon H. Tindemans, Peter Palensky
Generating power system states that have similar distribution and dependency to the historical ones is essential for the tasks of system planning and security assessment, especially when the historical data is insufficient.
1 code implementation • COLING 2022 • Jianhao Shen, Chenguang Wang, Linyuan Gong, Dawn Song
Unlike previous approaches that rely on either the structures or semantics of the knowledge graphs, we propose to jointly embed the semantics in the natural language description of the knowledge triplets with their structure information.
Ranked #3 on Link Prediction on UMLS
1 code implementation • 18 Oct 2022 • Zhiyuan Zhang, Lingjuan Lyu, Xingjun Ma, Chenguang Wang, Xu sun
In this work, we take the first step to exploit the pre-trained (unfine-tuned) weights to mitigate backdoors in fine-tuned language models.
no code implementations • 25 Oct 2022 • Chenguang Wang, Xiao Liu, Dawn Song
Instead of focusing on pre-defined relations, we create an OIE benchmark aiming to fully examine the open relational information present in the pre-trained LMs.
1 code implementation • 25 Oct 2022 • Jianhao Shen, Chenguang Wang, Ye Yuan, Jiawei Han, Heng Ji, Koushik Sen, Ming Zhang, Dawn Song
For instance, we outperform the fully finetuning approaches on a KG completion benchmark by tuning only 1% of the parameters.
Ranked #5 on Link Prediction on UMLS
1 code implementation • 26 Oct 2022 • Da Shen, Xinyun Chen, Chenguang Wang, Koushik Sen, Dawn Song
Our key observation is that existing language models pretrained on code still lack the understanding of code syntax.
no code implementations • 12 Nov 2022 • Weichen Zhao, Chenguang Wang, Congying Han, Tiande Guo
Results show that our proposed sufficient condition can effectively improve over-smoothing problem in operator-inconsistent GNN and enhance the performance of the model.
1 code implementation • 1 Mar 2023 • Chenguang Wang, Zhouliang Yu, Stephen Mcaleer, Tianshu Yu, Yaodong Yang
Applying machine learning to combinatorial optimization problems has the potential to improve both efficiency and accuracy.
no code implementations • 20 Mar 2023 • Chenguang Wang, Ensieh Sharifnia, Simon H. Tindemans, Peter Palensky
Variational autoencoder (VAE) neural networks can be trained to generate power system states that capture both marginal distribution and multivariate dependencies of historical data.
no code implementations • 10 May 2023 • Chenguang Wang, Tianshu Yu
Efficiently training a multi-task neural solver for various combinatorial optimization problems (COPs) has been less studied so far.
1 code implementation • ICCV 2023 • Myeongseob Ko, Ming Jin, Chenguang Wang, Ruoxi Jia
Furthermore, our enhanced attacks outperform the baseline across multiple models and datasets, with the weakly supervised attack demonstrating an average-case performance improvement of $17\%$ and being at least $7$X more effective at low false-positive rates.
no code implementations • 2 Oct 2023 • Chenguang Wang, Yepeng Liu, Xiaojian Zhang, Xuechun Li, Vladimir Paramygin, Arthriya Subgranon, Peter Sheng, Xilei Zhao, Susu Xu
We gathered and annotated building damage ground truth data in Lee County, Florida, and compared the introduced method's estimation results with the ground truth and benchmarked it against state-of-the-art models to assess the effectiveness of our proposed method.
1 code implementation • 5 Oct 2023 • Nicholas Crispino, Kyle Montgomery, Fankun Zeng, Dawn Song, Chenguang Wang
For instance, our method boosts the performance of state-of-the-art large language models by a large margin, including Vicuna-13b (13. 3%), Llama-2-70b-chat (23. 2%), and GPT-3. 5 Turbo (17. 0%).
no code implementations • 4 Dec 2023 • Chenguang Wang, Davis Engler, Xuechun Li, James Hou, David J. Wald, Kishor Jaiswal, Susu Xu
Traditional systems for estimating human loss in disasters often depend on manually collected early casualty reports from global media, a process that's labor-intensive and slow with notable time delays.
no code implementations • 2 Feb 2024 • Junlin Wu, Jiongxiao Wang, Chaowei Xiao, Chenguang Wang, Ning Zhang, Yevgeniy Vorobeychik
In addition, we observe that the simpler and more scalable rank-by-distance approaches are often competitive with the best, and on occasion significantly outperform gradient-based methods.
no code implementations • 23 Feb 2024 • Chenguang Wang, Xuanhao Pan, Tianshu Yu
This paper presents a novel approach to task grouping in Multitask Learning (MTL), advancing beyond existing methods by addressing key theoretical and practical limitations.
no code implementations • 23 Feb 2024 • Weichen Zhao, Chenguang Wang, Xinyan Wang, Congying Han, Tiande Guo, Tianshu Yu
This paper presents a novel study of the oversmoothing issue in diffusion-based Graph Neural Networks (GNNs).
1 code implementation • 27 Feb 2024 • Jianhao Shen, Ye Yuan, Srbuhi Mirzoyan, Ming Zhang, Chenguang Wang
Compared to existing datasets that often focus on examining expert-level ability, our dataset includes fundamental skills and questions designed based on the K-12 curriculum.
1 code implementation • 15 Mar 2024 • Chenguang Wang, Ruoxi Jia, Xin Liu, Dawn Song
We show that CLIP leads to a significant robustness drop compared to supervised ImageNet models on our benchmark, especially under synthetic distribution shift and adversarial attacks.
no code implementations • 21 Mar 2024 • Rakuten Group, Aaron Levine, Connie Huang, Chenguang Wang, Eduardo Batista, Ewa Szymanska, Hongyi Ding, Hou Wei Chou, Jean-François Pessiot, Johanes Effendi, Justin Chiu, Kai Torben Ohlhus, Karan Chopra, Keiji Shinzato, Koji Murakami, Lee Xiong, Lei Chen, Maki Kubota, Maksim Tkachenko, Miroku Lee, Naoki Takahashi, Prathyusha Jwalapuram, Ryutaro Tatsushima, Saurabh Jain, Sunil Kumar Yadav, Ting Cai, Wei-Te Chen, Yandi Xia, Yuki Nakayama, Yutaka Higashiyama
We introduce RakutenAI-7B, a suite of Japanese-oriented large language models that achieve the best performance on the Japanese LM Harness benchmarks among the open 7B models.
no code implementations • 3 Apr 2024 • Ye Yuan, Kexin Tang, Jianhao Shen, Ming Zhang, Chenguang Wang
This enables the direct comparison of the social understanding of large language models to humans, more specifically, elementary students.
no code implementations • CCL 2021 • Chenguang Wang, Hongfei Lin, Liang Yang
“对话风格能够反映对话者的属性, 例如情感、性别和教育背景等。在对话系统中, 通过理解用户的对话风格, 能够更好地对用户进行建模。同样的, 面对不同背景的用户, 对话机器人也应该使用不同的语言风格与之交流。语言表达风格是文本的内在属性, 然而现有的大多数文本风格迁移研究, 集中在英文领域, 在中文领域则研究较少。本文构建了三个可用于中文文本风格迁移研究的数据集, 并将多种已有的文本风格迁移方法应用于该数据集。同时, 本文提出了基于DeepStyle算法与Transformer的风格迁移模型, 通过预训练可以获得不同风格的隐层向量表示。并基于Transformer构建生成端模型, 在解码阶段, 通过重建源文本的方式, 保留生成文本的内容信息, 并且引入对立风格的嵌入表示, 使得模型能够生成不同风格的文本。实验结果表明, 本文提出的模型在构建的中文数据集上均优于现有模型。”