Search Results for author: Ying Liu

Found 46 papers, 13 papers with code

用计量风格学方法考察《水浒传》的作者争议问题——以罗贯中《平妖传》为参照(Quantitive Stylistics Based Research on the Controversy of the Author of “Tales of the Marshes”: Comparing with “Pingyaozhuan” of Luo Guanzhong)

no code implementations CCL 2020 Li Song, Ying Liu

《水浒传》是独著还是合著, 施耐庵和罗贯中是何关系一直存在争议。本文将其作者争议粗略归纳为施耐庵作、罗贯中作、施作罗续、罗作他续、施作罗改五种情况, 以罗贯中的《平妖传》为参照, 用假设检验、文本聚类、文本分类、波动风格计量等方法, 结合对文本内容的分析, 考察《水浒传》的写作风格, 试图为其作者身份认定提供参考。结果显示, 只有罗作他续的可能性大, 即前70回为罗贯中所作, 后由他人续写, 其他四种情况可能性都较小。

Cross-modal Contrastive Attention Model for Medical Report Generation

no code implementations COLING 2022 Xiao Song, Xiaodan Zhang, Junzhong Ji, Ying Liu, Pengxu Wei

Medical report automatic generation has gained increasing interest recently as a way to help radiologists write reports more efficiently.

Medical Report Generation

中文自然语言处理多任务中的职业性别偏见测量(Measurement of Occupational Gender Bias in Chinese Natural Language Processing Tasks)

no code implementations CCL 2022 Mengqing Guo, Jiali Li, Jishun Zhao, Shucheng Zhu, Ying Liu, Pengyuan Liu

“尽管悲观者认为, 职场中永远不可能存在性别平等。但随着人们观念的转变, 愈来愈多的人们相信, 职业的选择应只与个人能力相匹配, 而不应由个体的性别决定。目前已经发现自然语言处理的各个任务中都存在着职业性别偏见。但这些研究往往只针对特定的英文任务, 缺乏针对中文的、综合多任务的职业性别偏见测量研究。本文基于霍兰德职业模型, 从中文自然语言处理中常见的三个任务出发, 测量了词向量、共指消解和文本生成中的职业性别偏见, 发现不同任务中的职业性别偏见既有一定的共性, 又存在着独特的差异性。总体来看, 不同任务中的职业性别偏见反映了现实生活中人们对于不同性别所选择职业的刻板印象。此外, 在设计不同任务的偏见测量指标时, 还需要考虑如语体、词序等语言学要素的影响。”

Analysis of Gender Bias in Social Perception and Judgement Using Chinese Word Embeddings

no code implementations NAACL (GeBNLP) 2022 Jiali Li, Shucheng Zhu, Ying Liu, Pengyuan Liu

The results reveal that these grammatical gender-neutral Chinese word embeddings show a certain gender bias, which is consistent with the mainstream society’s perception and judgment of gender.

Word Embeddings

Metaphor Detection via Linguistics Enhanced Siamese Network

1 code implementation COLING 2022 Shenglong Zhang, Ying Liu

In this paper we present MisNet, a novel model for word level metaphor detection.

SaGE: 基于句法感知图卷积神经网络和ELECTRA的中文隐喻识别模型(SaGE: Syntax-aware GCN with ELECTRA for Chinese Metaphor Detection)

no code implementations CCL 2021 Shenglong Zhang, Ying Liu, Yanjun Ma

“隐喻是人类语言中经常出现的一种特殊现象, 隐喻识别对于自然语言处理各项任务来说具有十分基础和重要的意义。针对中文领域的隐喻识别任务, 我们提出了一种基于句法感知图卷积神经网络和ELECTRA的隐喻识别模型(Syntax-aware GCN withELECTRA SaGE)。该模型从语言学出发, 使用ELECTRA和Transformer编码器抽取句子的语义特征, 将句子按照依存关系组织成一张图并使用图卷积神经网络抽取其句法特征, 在此基础上对两类特征进行融合以进行隐喻识别。我们的模型在CCL2018中文隐喻识别评测数据集上以85. 22%的宏平均F1分数超越了此前的最佳成绩, 验证了融合语义信息和句法信息对于隐喻识别任务具有重要作用。”

RTN: Reinforced Transformer Network for Coronary CT Angiography Vessel-level Image Quality Assessment

no code implementations13 Jul 2022 Yiting Lu, Jun Fu, Xin Li, Wei Zhou, Sen Liu, Xinxin Zhang, Congfu Jia, Ying Liu, Zhibo Chen

Therefore, we propose a Progressive Reinforcement learning based Instance Discarding module (termed as PRID) to progressively remove quality-irrelevant/negative instances for CCTA VIQA.

Image Quality Assessment Multiple Instance Learning

RCMNet: A deep learning model assists CAR-T therapy for leukemia

no code implementations6 May 2022 Ruitao Zhang, Xueying Han, Ijaz Gul, Shiyao Zhai, Ying Liu, Yongbing Zhang, Yuhan Dong, Lan Ma, Dongmei Yu, Jin Zhou, Peiwu Qin

Although testing on the CAR-T cells dataset, a decent performance is observed, which is attributed to the limited size of the dataset.

Image Classification Transfer Learning

Covariate-informed Representation Learning to Prevent Posterior Collapse of iVAE

no code implementations9 Feb 2022 Young-geun Kim, Ying Liu, XueXin Wei

Though the identifiability is appealing, we show that iVAEs could have local minimum solution where observations and the approximated ICs are independent given covariates.-a phenomenon we referred to as the posterior collapse problem of iVAEs.

Representation Learning

Stock Movement Prediction Based on Bi-typed Hybrid-relational Market Knowledge Graph via Dual Attention Networks

1 code implementation11 Jan 2022 Yu Zhao, Huaming Du, Ying Liu, Shaopeng Wei, Xingyan Chen, Fuzhen Zhuang, Qing Li, Ji Liu, Gang Kou

Stock Movement Prediction (SMP) aims at predicting listed companies' stock future price trend, which is a challenging task due to the volatile nature of financial markets.

Implicit Relations Stock Prediction

CSSR: A Context-Aware Sequential Software Service Recommendation Model

1 code implementation20 Dec 2021 Mingwei Zhang, Jiayuan Liu, Weipu Zhang, Ke Deng, Hai Dong, Ying Liu

We propose a novel software service recommendation model to help users find their suitable repositories in GitHub.

Graph Embedding Sequential Recommendation

Automated assessment of disease severity of COVID-19 using artificial intelligence with synthetic chest CT

no code implementations11 Dec 2021 Mengqiu Liu, Ying Liu, Yidong Yang, Aiping Liu, Shana Li, Changbing Qu, Xiaohui Qiu, Yang Li, Weifu Lv, Peng Zhang, Jie Wen

Correlations between imaging findings and clinical lab tests suggested the value of this system as a potential tool to assess disease severity of COVID-19.

Data Augmentation Lesion Segmentation

Visual-Semantic Transformer for Scene Text Recognition

no code implementations2 Dec 2021 Xin Tang, Yongquan Lai, Ying Liu, Yuanyuan Fu, Rui Fang

In this work, we propose to model semantic and visual information jointly with a Visual-Semantic Transformer (VST).

Irregular Text Recognition Scene Text Recognition

Physically Explainable CNN for SAR Image Classification

1 code implementation27 Oct 2021 Zhongling Huang, Xiwen Yao, Ying Liu, Corneliu Octavian Dumitru, Mihai Datcu, Junwei Han

In this paper, we first propose a novel physically explainable convolutional neural network for SAR image classification, namely physics guided and injected learning (PGIL).

Classification Explainable Models +1

Low-Dose CT Denoising Using a Structure-Preserving Kernel Prediction Network

no code implementations31 May 2021 Lu Xu, Yuwei Zhang, Ying Liu, Daoye Wang, Mu Zhou, Jimmy Ren, Jingwei Wei, Zhaoxiang Ye

Low-dose CT has been a key diagnostic imaging modality to reduce the potential risk of radiation overdose to patient health.

Denoising

A Large-Scale Benchmark for Food Image Segmentation

2 code implementations12 May 2021 Xiongwei Wu, Xin Fu, Ying Liu, Ee-Peng Lim, Steven C. H. Hoi, Qianru Sun

Existing food image segmentation models are underperforming due to two reasons: (1) there is a lack of high quality food image datasets with fine-grained ingredient labels and pixel-wise location masks -- the existing datasets either carry coarse ingredient labels or are small in size; and (2) the complex appearance of food makes it difficult to localize and recognize ingredients in food images, e. g., the ingredients may overlap one another in the same image, and the identical ingredient may appear distinctly in different food images.

Ranked #2 on Semantic Segmentation on FoodSeg103 (using extra training data)

Image Segmentation Semantic Segmentation

K-PLUG: Knowledge-injected Pre-trained Language Model for Natural Language Understanding and Generation in E-Commerce

1 code implementation Findings (EMNLP) 2021 Song Xu, Haoran Li, Peng Yuan, Yujia Wang, Youzheng Wu, Xiaodong He, Ying Liu, BoWen Zhou

K-PLUG achieves new state-of-the-art results on a suite of domain-specific NLP tasks, including product knowledge base completion, abstractive product summarization, and multi-turn dialogue, significantly outperforms baselines across the board, which demonstrates that the proposed method effectively learns a diverse set of domain-specific knowledge for both language understanding and generation tasks.

Knowledge Base Completion Language Modelling +2

Coexistience of phononic six-fold, four-fold and three-fold excitations in ternary antimonide Zr3Ni3Sb4

no code implementations22 Feb 2021 Mingmin Zhong, Ying Liu, Feng Zhou, Minquan Kuang, Tie Yang, Xiaotian Wang, Gang Zhang

However, these materials are uncommon because these excitations in electronic systems are usually broken by spin-orbit coupling (SOC) and normally far from the Fermi level.

Materials Science

Identify Influential Spreaders in Asymmetrically Interacting Multiplex Networks

no code implementations5 Jan 2021 Qi Zeng, Ying Liu, Liming Pan, Ming Tang

Our work provides insights on the importance of nodes in the multiplex network and gives a feasible framework to investigate influential spreaders in the asymmetrically coevolving dynamics.

Physics and Society

K-PLUG: KNOWLEDGE-INJECTED PRE-TRAINED LANGUAGE MODEL FOR NATURAL LANGUAGE UNDERSTANDING AND GENERATION

1 code implementation1 Jan 2021 Song Xu, Haoran Li, Peng Yuan, Yujia Wang, Youzheng Wu, Xiaodong He, Ying Liu, BoWen Zhou

K-PLUG achieves new state-of-the-art results on a suite of domain-specific NLP tasks, including product knowledge base completion, abstractive product summarization, and multi-turn dialogue, significantly outperforms baselines across the board, which demonstrates that the proposed method effectively learns a diverse set of domain-specific knowledge for both language understanding and generation tasks.

Chatbot Knowledge Base Completion +4

A Knowledge Graph based Approach for Mobile Application Recommendation

no code implementations18 Sep 2020 Mingwei Zhang, Jia-Wei Zhao, Hai Dong, Ke Deng, Ying Liu

With the rapid prevalence of mobile devices and the dramatic proliferation of mobile applications (apps), app recommendation becomes an emergent task that would benefit both app users and stockholders.

graph construction

Casual inference of General Treatment Effects using Neural Networks with A Diverging Number of Confounders

no code implementations15 Sep 2020 Xiaohong Chen, Ying Liu, Shujie Ma, Zheng Zhang

The estimation of causal effects is a primary goal of behavioral, social, economic and biomedical sciences.

GL-GAN: Adaptive Global and Local Bilevel Optimization model of Image Generation

no code implementations6 Aug 2020 Ying Liu, Wenhong Cai, Xiaohui Yuan, Jinhai Xiang

Although Generative Adversarial Networks have shown remarkable performance in image generation, there are some challenges in image realism and convergence speed.

Bilevel Optimization Image Generation

Relation Extraction with Temporal Reasoning Based on Memory Augmented Distant Supervision

1 code implementation NAACL 2019 Jianhao Yan, Lin He, Ruqin Huang, Jian Li, Ying Liu

This paper formulates the problem of relation extraction with temporal reasoning and proposes a solution to predict whether two given entities participate in a relation at a given time spot.

Relation Extraction

Structured Semantic Model supported Deep Neural Network for Click-Through Rate Prediction

2 code implementations4 Dec 2018 Chenglei Niu, Guojing Zhong, Ying Liu, Yandong Zhang, Yongsheng Sun, Ailong He, Zhaoji Chen

With the rapid development of online advertising and recommendation systems, click-through rate prediction is expected to play an increasingly important role. Recently many DNN-based models which follow a similar Embedding&MLP paradigm have been proposed, and have achieved good result in image/voice and nlp fields.

Click-Through Rate Prediction Recommendation Systems

Multi-view Point Cloud Registration with Adaptive Convergence Threshold and its Application on 3D Model Retrieval

no code implementations25 Nov 2018 Yaochen Li, Ying Liu, Rui Sun, Rui Guo, Li Zhu, Yong Qi

In this paper, we propose a framework to reconstruct the 3D models by the multi-view point cloud registration algorithm with adaptive convergence threshold, and subsequently apply it to 3D model retrieval.

Point Cloud Registration Retrieval

A Comparison of 1-D and 2-D Deep Convolutional Neural Networks in ECG Classification

1 code implementation16 Oct 2018 Yunan Wu, Feng Yang, Ying Liu, Xuefan Zha, Shaofeng Yuan

Then, in order to alleviate the overfitting problem in two-dimensional network, we initialize AlexNet-like network with weights trained on ImageNet, to fit the training ECG images and fine-tune the model, and to further improve the accuracy and robustness of ECG classification.

ECG Classification General Classification

Auto-Encoding Knockoff Generator for FDR Controlled Variable Selection

1 code implementation27 Sep 2018 Ying Liu, Cheng Zheng

A new statistical procedure (Model-X \cite{candes2018}) has provided a way to identify important factors using any supervised learning method controlling for FDR.

Methodology

Improving brain computer interface performance by data augmentation with conditional Deep Convolutional Generative Adversarial Networks

no code implementations19 Jun 2018 Qiqi Zhang, Ying Liu

One of the big restrictions in brain computer interface field is the very limited training samples, it is difficult to build a reliable and usable system with such limited data.

Data Augmentation EEG +1

A Framework in CRM Customer Lifecycle: Identify Downward Trend and Potential Issues Detection

no code implementations25 Feb 2018 Kun Hu, Zhe Li, Ying Liu, Luyin Cheng, Qi Yang, Yan Li

In the first prediction part, we focus on predicting the downward trend, which is an earlier stage of the customer lifecycle compared to churn.

Causal Inference Management +1

Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications

8 code implementations12 Feb 2018 Haowen Xu, Wenxiao Chen, Nengwen Zhao, Zeyan Li, Jiahao Bu, Zhihan Li, Ying Liu, Youjian Zhao, Dan Pei, Yang Feng, Jie Chen, Zhaogang Wang, Honglin Qiao

To ensure undisrupted business, large Internet companies need to closely monitor various KPIs (e. g., Page Views, number of online users, and number of orders) of its Web applications, to accurately detect anomalies and trigger timely troubleshooting/mitigation.

Unsupervised Anomaly Detection

Deep Reinforcement Learning for Dynamic Treatment Regimes on Medical Registry Data

no code implementations28 Jan 2018 Ning Liu, Ying Liu, Brent Logan, Zhiyuan Xu, Jian Tang, Yanzhi Wang

This paper presents the first deep reinforcement learning (DRL) framework to estimate the optimal Dynamic Treatment Regimes from observational medical data.

reinforcement-learning reinforcement Learning

Three IQs of AI Systems and their Testing Methods

no code implementations14 Dec 2017 Feng Liu, Yong Shi, Ying Liu

The rapid development of artificial intelligence has brought the artificial intelligence threat theory as well as the problem about how to evaluate the intelligence level of intelligent products.

Intelligence Quotient and Intelligence Grade of Artificial Intelligence

no code implementations29 Sep 2017 Feng Liu, Yong Shi, Ying Liu

Although artificial intelligence is currently one of the most interesting areas in scientific research, the potential threats posed by emerging AI systems remain a source of persistent controversy.

Two-dimensional Spin-Orbit Dirac Point in Monolayer HfGeTe

no code implementations27 Jun 2017 Shan Guan, Ying Liu, Zhi-Ming Yu, Shan-Shan Wang, Yugui Yao, Shengyuan A. Yang

However, the Dirac points in existing 2D materials, including graphene, are vulnerable against spin-orbit coupling (SOC).

Materials Science

Image Type Water Meter Character Recognition Based on Embedded DSP

no code implementations27 Aug 2015 Ying Liu, Yan-bin Han, Yu-lin Zhang

In the paper, we combined DSP processor with image processing algorithm and studied the method of water meter character recognition.

Meter Reading

Learning Gaussian Graphical Models with Observed or Latent FVSs

no code implementations NeurIPS 2013 Ying Liu, Alan S. Willsky

Exact inference such as computing the marginal distributions and the partition function has complexity $O(k^{2}n)$ using message-passing algorithms, where k is the size of the FVS, and n is the total number of nodes.

Cannot find the paper you are looking for? You can Submit a new open access paper.