Search Results for author: Qian Li

Found 40 papers, 11 papers with code

How Does Knowledge Graph Embedding Extrapolate to Unseen Data: a Semantic Evidence View

no code implementations24 Sep 2021 Ren Li, Yanan Cao, Qiannan Zhu, Guanqun Bi, Fang Fang, Yi Liu, Qian Li

However, most existing KGE works focus on the design of delicate triple modeling function, which mainly tell us how to measure the plausibility of observed triples, but we have limited understanding of why the methods can extrapolate to unseen data, and what are the important factors to help KGE extrapolate.

Knowledge Graph Completion Knowledge Graph Embedding

Event Extraction by Associating Event Types and Argument Roles

no code implementations23 Aug 2021 Qian Li, Shu Guo, Jia Wu, JianXin Li, Jiawei Sheng, Lihong Wang, Xiaohan Dong, Hao Peng

It ignores meaningful associations among event types and argument roles, leading to relatively poor performance for less frequent types/roles.

Document-level Event Extraction +2

AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer

2 code implementations ICCV 2021 Songhua Liu, Tianwei Lin, Dongliang He, Fu Li, Meiling Wang, Xin Li, Zhengxing Sun, Qian Li, Errui Ding

Finally, the content feature is normalized so that they demonstrate the same local feature statistics as the calculated per-point weighted style feature statistics.

Style Transfer Video Style Transfer

A Comprehensive Survey on Schema-based Event Extraction with Deep Learning

no code implementations5 Jul 2021 Qian Li, Hao Peng, JianXin Li, Yiming Hei, Rui Sun, Jiawei Sheng, Shu Guo, Lihong Wang, Jia Wu, Amin Beheshti, Philip S. Yu

Numerous methods, datasets, and evaluation metrics have been proposed in the literature, raising the need for a comprehensive and updated survey.

Event Extraction

CasEE: A Joint Learning Framework with Cascade Decoding for Overlapping Event Extraction

1 code implementation4 Jul 2021 Jiawei Sheng, Shu Guo, Bowen Yu, Qian Li, Yiming Hei, Lihong Wang, Tingwen Liu, Hongbo Xu

Event extraction (EE) is a crucial information extraction task that aims to extract event information in texts.

Event Extraction

Reinforcement Learning-based Dialogue Guided Event Extraction to Exploit Argument Relations

1 code implementation23 Jun 2021 Qian Li, Hao Peng, JianXin Li, Yuanxing Ning, Lihong Wang, Philip S. Yu, Zheng Wang

Our approach leverages knowledge of the already extracted arguments of the same sentence to determine the role of arguments that would be difficult to decide individually.

Event Extraction Incremental Learning

Stochastic Intervention for Causal Inference via Reinforcement Learning

no code implementations28 May 2021 Tri Dung Duong, Qian Li, Guandong Xu

In our study, we advance the causal inference research by proposing a new effective framework to estimate the treatment effect on stochastic intervention.

Causal Inference Decision Making

Stochastic Intervention for Causal Effect Estimation

no code implementations27 May 2021 Tri Dung Duong, Qian Li, Guandong Xu

Central to these applications is the treatment effect estimation of intervention strategies.

Causal Inference Decision Making

Be Causal: De-biasing Social Network Confounding in Recommendation

no code implementations17 May 2021 Qian Li, Xiangmeng Wang, Guandong Xu

A common practice to address MNAR is to treat missing entries from the so-called "exposure" perspective, i. e., modeling how an item is exposed (provided) to a user.

Causal Inference Recommendation Systems +2

High Accuracy and Low Complexity Frequency Offset Estimation Based on All-Phase FFT for M-QAM Coherent Optical Systems

no code implementations15 May 2021 Qian Li

A low complexity frequency offset estimation algorithm based on all-phase FFT for M-QAM is proposed.

Prototype-based Counterfactual Explanation for Causal Classification

1 code implementation3 May 2021 Tri Dung Duong, Qian Li, Guandong Xu

Counterfactual explanation is one branch of interpretable machine learning that produces a perturbation sample to change the model's original decision.

Classification Counterfactual Explanation +2

Few-shot Continual Learning: a Brain-inspired Approach

no code implementations19 Apr 2021 Liyuan Wang, Qian Li, Yi Zhong, Jun Zhu

Our solution is based on the observation that continual learning of a task sequence inevitably interferes few-shot generalization, which makes it highly nontrivial to extend few-shot learning strategies to continual learning scenarios.

Continual Learning Few-Shot Learning

A General Framework for Learning Prosodic-Enhanced Representation of Rap Lyrics

no code implementations23 Mar 2021 Hongru Liang, Haozheng Wang, Qian Li, Jun Wang, Guandong Xu, Jiawei Chen, Jin-Mao Wei, Zhenglu Yang

Learning and analyzing rap lyrics is a significant basis for many web applications, such as music recommendation, automatic music categorization, and music information retrieval, due to the abundant source of digital music in the World Wide Web.

Information Retrieval Music Information Retrieval +1

Improving Generalizability in Limited-Angle CT Reconstruction with Sinogram Extrapolation

no code implementations9 Mar 2021 Ce Wang, Haimiao Zhang, Qian Li, Kun Shang, Yuanyuan Lyu, Bin Dong, S. Kevin Zhou

More importantly, we show that using such a sinogram extrapolation module significantly improves the generalization capability of the model on unseen datasets (e. g., COVID-19 and LIDC datasets) when compared to existing approaches.

Computed Tomography (CT)

Video Face Recognition System: RetinaFace-mnet-faster and Secondary Search

no code implementations28 Sep 2020 Qian Li, Nan Guo, Xiaochun Ye, Dongrui Fan, Zhimin Tang

Ours is suitable for large-scale datasets, and experimental results show that our method is 82% faster than the violent retrieval for the single-frame detection.

Face Recognition

Leveraging Multi-level Dependency of Relational Sequences for Social Spammer Detection

no code implementations14 Sep 2020 Jun Yin, Qian Li, Shaowu Liu, Zhiang Wu, Guandong Xu

Our study investigates the spammer detection problem in the context of multi-relation social networks, and makes an attempt to fully exploit the sequences of heterogeneous relations for enhancing the detection accuracy.

Top-Related Meta-Learning Method for Few-Shot Object Detection

1 code implementation14 Jul 2020 Qian Li, Nan Guo, Xiaochun Ye, Duo Wang, Dongrui Fan, Zhimin Tang

Therefore, based on semantic features, we propose a Top-C classification loss (i. e., TCL-C) for classification task and a category-based grouping mechanism for category-based meta-features obtained by the meta-model.

Few-Shot Object Detection Meta-Learning

Causality Learning: A New Perspective for Interpretable Machine Learning

no code implementations27 Jun 2020 Guandong Xu, Tri Dung Duong, Qian Li, Shaowu Liu, Xianzhi Wang

Recent years have witnessed the rapid growth of machine learning in a wide range of fields such as image recognition, text classification, credit scoring prediction, recommendation system, etc.

Interpretable Machine Learning Text Classification

Stochastic Batch Augmentation with An Effective Distilled Dynamic Soft Label Regularizer

no code implementations27 Jun 2020 Qian Li, Qingyuan Hu, Yong Qi, Saiyu Qi, Jie Ma, Jian Zhang

SBA stochastically decides whether to augment at iterations controlled by the batch scheduler and in which a ''distilled'' dynamic soft label regularization is introduced by incorporating the similarity in the vicinity distribution respect to raw samples.

Data Augmentation

Weakly Supervised Context Encoder using DICOM metadata in Ultrasound Imaging

no code implementations20 Mar 2020 Szu-Yeu Hu, Shuhang Wang, Wei-Hung Weng, JingChao Wang, XiaoHong Wang, Arinc Ozturk, Qian Li, Viksit Kumar, Anthony E. Samir

Modern deep learning algorithms geared towards clinical adaption rely on a significant amount of high fidelity labeled data.

Neighborhood Information-based Probabilistic Algorithm for Network Disintegration

no code implementations8 Mar 2020 Qian Li, San-Yang Liu, Xin-She Yang

Network structure and integrity can be controlled by a set of key nodes, and to find the optimal combination of nodes in a network to ensure network structure and integrity can be an NP-complete problem.

Protein Folding

Influence of Initialization on the Performance of Metaheuristic Optimizers

no code implementations8 Mar 2020 Qian Li, San-Yang Liu, Xin-She Yang

Differential evolution depends more heavily on the number of iterations, a relatively small population with more iterations can lead to better results.

Metaheuristic Optimization

Triple Memory Networks: a Brain-Inspired Method for Continual Learning

no code implementations6 Mar 2020 Liyuan Wang, Bo Lei, Qian Li, Hang Su, Jun Zhu, Yi Zhong

Continual acquisition of novel experience without interfering previously learned knowledge, i. e. continual learning, is critical for artificial neural networks, but limited by catastrophic forgetting.

class-incremental learning Hippocampus +1

Answer-Supervised Question Reformulation for Enhancing Conversational Machine Comprehension

no code implementations WS 2019 Qian Li, Hui Su, Cheng Niu, Daling Wang, Zekang Li, Shi Feng, Yifei Zhang

Moreover, pretraining is essential in reinforcement learning models, so we provide a high-quality annotated dataset for question reformulation by sampling a part of QuAC dataset.

Reading Comprehension

Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation

no code implementations27 Aug 2019 Nima Tajbakhsh, Laura Jeyaseelan, Qian Li, Jeffrey Chiang, Zhihao Wu, Xiaowei Ding

The medical imaging literature has witnessed remarkable progress in high-performing segmentation models based on convolutional neural networks.

Medical Image Segmentation

Are You for Real? Detecting Identity Fraud via Dialogue Interactions

1 code implementation IJCNLP 2019 Weikang Wang, Jiajun Zhang, Qian Li, Cheng-qing Zong, Zhifei Li

In this paper, we focus on identity fraud detection in loan applications and propose to solve this problem with a novel interactive dialogue system which consists of two modules.

Dialogue Management Fraud Detection

Incremental Transformer with Deliberation Decoder for Document Grounded Conversations

1 code implementation ACL 2019 Zekang Li, Cheng Niu, Fandong Meng, Yang Feng, Qian Li, Jie zhou

Document Grounded Conversations is a task to generate dialogue responses when chatting about the content of a given document.

INFaaS: A Model-less and Managed Inference Serving System

1 code implementation30 May 2019 Francisco Romero, Qian Li, Neeraja J. Yadwadkar, Christos Kozyrakis

This paper introduces INFaaS, a managed and model-less system for distributed inference serving, where developers simply specify the performance and accuracy requirements for their applications without needing to specify a specific model-variant for each query.

Model Selection

Joint Entity Linking with Deep Reinforcement Learning

no code implementations1 Feb 2019 Zheng Fang, Yanan Cao, Dongjie Zhang, Qian Li, Zhen-Yu Zhang, Yanbing Liu

Entity linking is the task of aligning mentions to corresponding entities in a given knowledge base.

Entity Linking

A Multi-Attention based Neural Network with External Knowledge for Story Ending Predicting Task

no code implementations COLING 2018 Qian Li, Ziwei Li, Jin-Mao Wei, Yanhui Gu, Adam Jatowt, Zhenglu Yang

Enabling a mechanism to understand a temporal story and predict its ending is an interesting issue that has attracted considerable attention, as in case of the ROC Story Cloze Task (SCT).

Common Sense Reasoning Feature Engineering +1

Efficient Delivery Policy to Minimize User Traffic Consumption in Guaranteed Advertising

no code implementations23 Nov 2016 Jia Zhang, Zheng Wang, Qian Li, Jialin Zhang, Yanyan Lan, Qiang Li, Xiaoming Sun

In the guaranteed delivery scenario, ad exposures (which are also called impressions in some works) to users are guaranteed by contracts signed in advance between advertisers and publishers.

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