no code implementations • CCL 2021 • Ning Yu, Jiangping Wang, Yu Shi, Jianyi Liu
“本文利用知网(HowNet)中的知识, 并将Word2vec模型的结构和思想迁移至义原表示学习过程中, 提出了一个基于义原表示学习的词向量表示方法。首先, 本文利用OpenHowNet获取义原知识库中的所有义原、所有中文词汇以及所有中文词汇和其对应的义原集合, 作为实验的数据集。然后, 基于Skip-gram模型, 训练义原表示学习模型, 进而获得词向量。最后, 通过词相似度任务、词义消歧任务、词汇类比和观察最近邻义原, 来评价本文提出的方法获取的词向量的效果。通过和基线模型比较, 发现本文提出的方法既高效又准确, 不依赖大规模语料也不需要复杂的网络结构和繁多的参数, 也能提升各种自然语言处理任务的准确率。”
no code implementations • 29 Feb 2024 • Tony C. W. Mok, Zi Li, Yunhao Bai, Jianpeng Zhang, Wei Liu, Yan-Jie Zhou, Ke Yan, Dakai Jin, Yu Shi, Xiaoli Yin, Le Lu, Ling Zhang
Existing multi-modality image registration algorithms rely on statistical-based similarity measures or local structural image representations.
no code implementations • 27 Feb 2024 • Jiaqi Zhai, Lucy Liao, Xing Liu, Yueming Wang, Rui Li, Xuan Cao, Leon Gao, Zhaojie Gong, Fangda Gu, Michael He, Yinghai Lu, Yu Shi
Large-scale recommendation systems are characterized by their reliance on high cardinality, heterogeneous features and the need to handle tens of billions of user actions on a daily basis.
no code implementations • 9 Nov 2023 • Yu Shi, Hannah Tang, Michael Baine, Michael A. Hollingsworth, Huijing Du, Dandan Zheng, Chi Zhang, Hongfeng Yu
Furthermore, this model has the potential to be adapted to other types of solid tumors, hence making significant contributions to the field of medical imaging in terms of image processing models.
no code implementations • 31 Aug 2023 • Yu Shi, Dong-Dong Wu, Xin Geng, Min-Ling Zhang
This is known as Unreliable Partial Label Learning (UPLL) that introduces an additional complexity due to the inherent unreliability and ambiguity of partial labels, often resulting in a sub-optimal performance with existing methods.
no code implementations • 9 Aug 2023 • Fan Bai, Ke Yan, Xiaoyu Bai, Xinyu Mao, Xiaoli Yin, Jingren Zhou, Yu Shi, Le Lu, Max Q. -H. Meng
We evaluate our method on liver tumor segmentation and achieve state-of-the-art performance, outperforming traditional fine-tuning with only 6% of tunable parameters, also achieving 94% of full-data performance by labeling only 5% of the data.
no code implementations • 1 Aug 2023 • Hexin Dong, Jiawen Yao, Yuxing Tang, Mingze Yuan, Yingda Xia, Jian Zhou, Hong Lu, Jingren Zhou, Bin Dong, Le Lu, Li Zhang, Zaiyi Liu, Yu Shi, Ling Zhang
Pancreatic ductal adenocarcinoma (PDAC) is a highly lethal cancer in which the tumor-vascular involvement greatly affects the resectability and, thus, overall survival of patients.
1 code implementation • 17 Jul 2023 • Ke Yan, Xiaoli Yin, Yingda Xia, Fakai Wang, Shu Wang, Yuan Gao, Jiawen Yao, Chunli Li, Xiaoyu Bai, Jingren Zhou, Ling Zhang, Le Lu, Yu Shi
Liver tumor segmentation and classification are important tasks in computer aided diagnosis.
no code implementations • 8 Jun 2023 • Shuxin Zheng, Jiyan He, Chang Liu, Yu Shi, Ziheng Lu, Weitao Feng, Fusong Ju, Jiaxi Wang, Jianwei Zhu, Yaosen Min, He Zhang, Shidi Tang, Hongxia Hao, Peiran Jin, Chi Chen, Frank Noé, Haiguang Liu, Tie-Yan Liu
In this paper, we introduce a novel deep learning framework, called Distributional Graphormer (DiG), in an attempt to predict the equilibrium distribution of molecular systems.
no code implementations • 24 May 2023 • Zhuokai Zhao, Yang Yang, Wenyu Wang, Chihuang Liu, Yu Shi, Wenjie Hu, Haotian Zhang, Shuang Yang
A key puzzle in search, ads, and recommendation is that the ranking model can only utilize a small portion of the vastly available user interaction data.
no code implementations • 21 May 2023 • ZiYi Yang, Mahmoud Khademi, Yichong Xu, Reid Pryzant, Yuwei Fang, Chenguang Zhu, Dongdong Chen, Yao Qian, Mei Gao, Yi-Ling Chen, Robert Gmyr, Naoyuki Kanda, Noel Codella, Bin Xiao, Yu Shi, Lu Yuan, Takuya Yoshioka, Michael Zeng, Xuedong Huang
The convergence of text, visual, and audio data is a key step towards human-like artificial intelligence, however the current Vision-Language-Speech landscape is dominated by encoder-only models which lack generative abilities.
no code implementations • CVPR 2023 • Mingze Yuan, Yingda Xia, Hexin Dong, ZiFan Chen, Jiawen Yao, Mingyan Qiu, Ke Yan, Xiaoli Yin, Yu Shi, Xin Chen, Zaiyi Liu, Bin Dong, Jingren Zhou, Le Lu, Ling Zhang, Li Zhang
Real-world medical image segmentation has tremendous long-tailed complexity of objects, among which tail conditions correlate with relatively rare diseases and are clinically significant.
no code implementations • 20 Mar 2023 • Haibin Yu, Yuxuan Hu, Yao Qian, Ma Jin, Linquan Liu, Shujie Liu, Yu Shi, Yanmin Qian, Edward Lin, Michael Zeng
Code-switching speech refers to a means of expression by mixing two or more languages within a single utterance.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 20 Feb 2023 • Yu Shi, Ning Xu, Hua Yuan, Xin Geng
Therefore, a generalized PLL named Unreliable Partial Label Learning (UPLL) is proposed, in which the true label may not be in the candidate label set.
1 code implementation • 4 Feb 2023 • Min Peng, Chongyang Wang, Yu Shi, Xiang-Dong Zhou
This paper presents a new method for end-to-end Video Question Answering (VideoQA), aside from the current popularity of using large-scale pre-training with huge feature extractors.
no code implementations • ICCV 2023 • Jieneng Chen, Yingda Xia, Jiawen Yao, Ke Yan, Jianpeng Zhang, Le Lu, Fakai Wang, Bo Zhou, Mingyan Qiu, Qihang Yu, Mingze Yuan, Wei Fang, Yuxing Tang, Minfeng Xu, Jian Zhou, Yuqian Zhao, Qifeng Wang, Xianghua Ye, Xiaoli Yin, Yu Shi, Xin Chen, Jingren Zhou, Alan Yuille, Zaiyi Liu, Ling Zhang
Human readers or radiologists routinely perform full-body multi-organ multi-disease detection and diagnosis in clinical practice, while most medical AI systems are built to focus on single organs with a narrow list of a few diseases.
no code implementations • 4 Jan 2023 • Zhilin Zheng, Xu Fang, Jiawen Yao, Mengmeng Zhu, Le Lu, Lingyun Huang, Jing Xiao, Yu Shi, Hong Lu, Jianping Lu, Ling Zhang, Chengwei Shao, Yun Bian
Lymph node (LN) metastasis status is one of the most critical prognostic and cancer staging factors for patients with resectable pancreatic ductal adenocarcinoma (PDAC), or in general, for any types of solid malignant tumors.
no code implementations • 11 Nov 2022 • Xiaofei Wang, Zhuo Chen, Yu Shi, Jian Wu, Naoyuki Kanda, Takuya Yoshioka
Employing a monaural speech separation (SS) model as a front-end for automatic speech recognition (ASR) involves balancing two kinds of trade-offs.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
1 code implementation • 21 Aug 2022 • Pengcheng He, Baolin Peng, Liyang Lu, Song Wang, Jie Mei, Yang Liu, Ruochen Xu, Hany Hassan Awadalla, Yu Shi, Chenguang Zhu, Wayne Xiong, Michael Zeng, Jianfeng Gao, Xuedong Huang
Z-Code++ creates new state of the art on 9 out of 13 text summarization tasks across 5 languages.
1 code implementation • 19 Aug 2022 • Yaosen Min, Ye Wei, Peizhuo Wang, Xiaoting Wang, Han Li, Nian Wu, Stefan Bauer, Shuxin Zheng, Yu Shi, Yingheng Wang, Ji Wu, Dan Zhao, Jianyang Zeng
Accurate prediction of the protein-ligand binding affinities is an essential challenge in the structure-based drug design.
2 code implementations • 20 Jul 2022 • Yu Shi, Guolin Ke, Zhuoming Chen, Shuxin Zheng, Tie-Yan Liu
Recent years have witnessed significant success in Gradient Boosting Decision Trees (GBDT) for a wide range of machine learning applications.
no code implementations • 23 Jun 2022 • Xia Hua, Mingxin Li, Junxiong Fei, Yu Shi, Jianguo Liu, Hanyu Hong
In most of these networks, only the features refined by the attention maps can be passed to the next layer and the attention maps of different layers are separated from each other, which does not make full use of the attention information from different layers in the CNN.
1 code implementation • 9 May 2022 • Min Peng, Chongyang Wang, Yuan Gao, Yu Shi, Xiang-Dong Zhou
With a multiscale sampling, RMI iterates the interaction of appearance-motion information at each scale and the question embeddings to build the multilevel question-guided visual representations.
no code implementations • 3 May 2022 • ZiYi Yang, Yuwei Fang, Chenguang Zhu, Reid Pryzant, Dongdong Chen, Yu Shi, Yichong Xu, Yao Qian, Mei Gao, Yi-Ling Chen, Liyang Lu, Yujia Xie, Robert Gmyr, Noel Codella, Naoyuki Kanda, Bin Xiao, Lu Yuan, Takuya Yoshioka, Michael Zeng, Xuedong Huang
Human intelligence is multimodal; we integrate visual, linguistic, and acoustic signals to maintain a holistic worldview.
3 code implementations • 9 Mar 2022 • Yu Shi, Shuxin Zheng, Guolin Ke, Yifei Shen, Jiacheng You, Jiyan He, Shengjie Luo, Chang Liu, Di He, Tie-Yan Liu
This technical note describes the recent updates of Graphormer, including architecture design modifications, and the adaption to 3D molecular dynamics simulation.
no code implementations • 28 Feb 2022 • Yu Shi, Shuxin Zheng, Guolin Ke, Yifei Shen, Jiacheng You, Jiyan He, Shengjie Luo, Chang Liu, Di He, Tie-Yan Liu
This technical note describes the recent updates of Graphormer, including architecture design modifications, and the adaption to 3D molecular dynamics simulation.
no code implementations • 10 Dec 2021 • Kenichi Kumatani, Robert Gmyr, Felipe Cruz Salinas, Linquan Liu, Wei Zuo, Devang Patel, Eric Sun, Yu Shi
The sparsely-gated Mixture of Experts (MoE) can magnify a network capacity with a little computational complexity.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
1 code implementation • 22 Nov 2021 • Lu Yuan, Dongdong Chen, Yi-Ling Chen, Noel Codella, Xiyang Dai, Jianfeng Gao, Houdong Hu, Xuedong Huang, Boxin Li, Chunyuan Li, Ce Liu, Mengchen Liu, Zicheng Liu, Yumao Lu, Yu Shi, Lijuan Wang, JianFeng Wang, Bin Xiao, Zhen Xiao, Jianwei Yang, Michael Zeng, Luowei Zhou, Pengchuan Zhang
Computer vision foundation models, which are trained on diverse, large-scale dataset and can be adapted to a wide range of downstream tasks, are critical for this mission to solve real-world computer vision applications.
Ranked #1 on Action Recognition In Videos on Kinetics-600
1 code implementation • 10 Sep 2021 • Min Peng, Chongyang Wang, Yuan Gao, Yu Shi, Xiang-Dong Zhou
Targeting these issues, this paper proposes a novel Temporal Pyramid Transformer (TPT) model with multimodal interaction for VideoQA.
no code implementations • 25 Jul 2021 • Linhao Zhang, Yu Shi, Linjun Shou, Ming Gong, Houfeng Wang, Michael Zeng
In this paper, we attempt to bridge these two lines of research and propose a joint and domain adaptive approach to SLU.
no code implementations • 2 Jul 2021 • Yu Shi
The Transformer model is widely used in natural language processing for sentence representation.
no code implementations • 29 Mar 2021 • Qixuan Luo, Yu Shi, Handong Li
The permanent impact generated by an asset in the portfolio during the liquidation will affect all assets, and the temporary impact generated by one asset will only affect itself.
no code implementations • 22 Feb 2021 • Junwei Liao, Yu Shi, Ming Gong, Linjun Shou, Sefik Eskimez, Liyang Lu, Hong Qu, Michael Zeng
Many downstream tasks and human readers rely on the output of the ASR system; therefore, errors introduced by the speaker and ASR system alike will be propagated to the next task in the pipeline.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 12 Feb 2021 • Junwei Liao, Yu Shi, Ming Gong, Linjun Shou, Hong Qu, Michael Zeng
However, the performance of using multiple encoders and decoders on zero-shot translation still lags behind universal NMT.
no code implementations • 11 Feb 2021 • Yao Qian, Ximo Bian, Yu Shi, Naoyuki Kanda, Leo Shen, Zhen Xiao, Michael Zeng
End-to-end (E2E) spoken language understanding (SLU) can infer semantics directly from speech signal without cascading an automatic speech recognizer (ASR) with a natural language understanding (NLU) module.
Ranked #3 on Spoken Language Understanding on Fluent Speech Commands (using extra training data)
no code implementations • 19 Jan 2021 • Yu Shi, Edo Waks
Cluster states are useful in many quantum information processing applications.
Quantum Physics
1 code implementation • Asian Chapter of the Association for Computational Linguistics 2020 • Ruochen Xu, Chenguang Zhu, Yu Shi, Michael Zeng, Xuedong Huang
Cross-lingual Summarization (CLS) aims at producing a summary in the target language for an article in the source language.
no code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Huaishao Luo, Yu Shi, Ming Gong, Linjun Shou, Tianrui Li
In this paper, we propose a novel approach that extends the probability vector to a probability matrix.
1 code implementation • 21 Sep 2020 • Naveed Ahmed Azam, Jianshen Zhu, Yanming Sun, Yu Shi, Aleksandar Shurbevski, Liang Zhao, Hiroshi Nagamochi, Tatsuya Akutsu
In the second phase, given a target value $y^*$ of property $\pi$, a feature vector $x^*$ is inferred by solving an MILP formulated from the trained ANN so that $\psi(x^*)$ is close to $y^*$ and then a set of chemical structures $G^*$ such that $f(G^*)= x^*$ is enumerated by a graph search algorithm.
Data Structures and Algorithms Computational Engineering, Finance, and Science 05C92, 92E10, 05C30, 68T07, 90C11, 92-04
1 code implementation • 19 Sep 2020 • Min Peng, Chongyang Wang, Yuan Gao, Tao Bi, Tong Chen, Yu Shi, Xiang-Dong Zhou
As a spontaneous expression of emotion on face, micro-expression reveals the underlying emotion that cannot be controlled by human.
no code implementations • 26 Aug 2020 • Jiawen Yao, Yu Shi, Le Lu, Jing Xiao, Ling Zhang
We present a multi-task CNN to accomplish both tasks of outcome and margin prediction where the network benefits from learning the tumor resection margin related features to improve survival prediction.
no code implementations • 24 Aug 2020 • Ling Zhang, Yu Shi, Jiawen Yao, Yun Bian, Kai Cao, Dakai Jin, Jing Xiao, Le Lu
A student model is trained on both manual and pseudo annotated multi-phase images.
no code implementations • 9 Jun 2020 • Wei Wu, Yu Shi, Xukun Li, Yukun Zhou, Peng Du, Shuangzhi Lv, Tingbo Liang, Jifang Sheng
For the segmented masks of intact lung and infected regions, the best method could achieve 0. 972 and 0. 757 measure in mean Dice similarity coefficient on our test benchmark.
no code implementations • 9 Apr 2020 • Junwei Liao, Sefik Emre Eskimez, Liyang Lu, Yu Shi, Ming Gong, Linjun Shou, Hong Qu, Michael Zeng
In this work, we propose a novel NLP task called ASR post-processing for readability (APR) that aims to transform the noisy ASR output into a readable text for humans and downstream tasks while maintaining the semantic meaning of the speaker.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • ICLR 2020 • Ruixuan Zhang, Zhuoyu Wei, Yu Shi, Yining Chen
When we apply BERT to long text tasks, e. g., document-level text summarization: 1) Truncating inputs by the maximum sequence length will decrease performance, since the model cannot capture long dependency and global information ranging the whole document.
no code implementations • 29 Sep 2019 • Carl Yang, Yichen Feng, Pan Li, Yu Shi, Jiawei Han
In this work, we propose to study the utility of different meta-graphs, as well as how to simultaneously leverage multiple meta-graphs for HIN embedding in an unsupervised manner.
1 code implementation • 4 Sep 2019 • Yu Shi, Jiaming Shen, Yuchen Li, Naijing Zhang, Xinwei He, Zhengzhi Lou, Qi Zhu, Matthew Walker, Myunghwan Kim, Jiawei Han
Extensive experiments on two large real-world datasets demonstrate the effectiveness of HyperMine and the utility of modeling context granularity.
1 code implementation • 7 Apr 2019 • Min Peng, Chongyang Wang, Tao Bi, Tong Chen, Xiangdong Zhou, Yu Shi
As researchers working on such topics are moving to learn from the nature of micro-expression, the practice of using deep learning techniques has evolved from processing the entire video clip of micro-expression to the recognition on apex frame.
1 code implementation • 28 Nov 2018 • Yu Shi, Xinwei He, Naijing Zhang, Carl Yang, Jiawei Han
We therefore approach the problem of user-guided clustering in HINs with network motifs.
1 code implementation • 10 Jul 2018 • Yu Shi, Qi Zhu, Fang Guo, Chao Zhang, Jiawei Han
To cope with the challenges in the comprehensive transcription of HINs, we propose the HEER algorithm, which embeds HINs via edge representations that are further coupled with properly-learned heterogeneous metrics.
no code implementations • 25 May 2018 • Tyler W. Hughes, Momchil Minkov, Yu Shi, Shanhui Fan
Recently, integrated optics has gained interest as a hardware platform for implementing machine learning algorithms.
no code implementations • 5 Mar 2018 • Yu Shi, Huan Gui, Qi Zhu, Lance Kaplan, Jiawei Han
Therefore, we are motivated to propose a novel embedding learning framework---AspEm---to preserve the semantic information in HINs based on multiple aspects.
1 code implementation • 15 Feb 2018 • Yu Shi, Jian Li, Zhize Li
We show that PL Trees can accelerate convergence of GBDT and improve the accuracy.
1 code implementation • 19 Jan 2018 • Yu Shi, Fangqiu Han, Xinwei He, Xinran He, Carl Yang, Jie Luo, Jiawei Han
With experiments on a series of synthetic datasets, a large-scale internal Snapchat dataset, and two public datasets, we confirm the validity and importance of preservation and collaboration as two objectives for multi-view network embedding.
no code implementations • 5 Jun 2017 • Yu Shi, Po-Wei Chan, Honglei Zhuang, Huan Gui, Jiawei Han
We also identify, from real-world data, and propose to model cross-meta-path synergy, which is a characteristic important for defining path-based HIN relevance and has not been modeled by existing methods.