Search Results for author: Heng Zhang

Found 30 papers, 7 papers with code

Less Is More: Domain Adaptation with Lottery Ticket for Reading Comprehension

1 code implementation Findings (EMNLP) 2021 Haichao Zhu, Zekun Wang, Heng Zhang, Ming Liu, Sendong Zhao, Bing Qin

Then, we only fine-tune the lottery subnetwork, a small fraction of the whole parameters, on the annotated target domain data for adaptation.

Domain Adaptation Reading Comprehension

Document-level Event Factuality Identification via Machine Reading Comprehension Frameworks with Transfer Learning

no code implementations COLING 2022 Zhong Qian, Heng Zhang, Peifeng Li, Qiaoming Zhu, Guodong Zhou

Document-level Event Factuality Identification (DEFI) predicts the factuality of a specific event based on a document from which the event can be derived, which is a fundamental and crucial task in Natural Language Processing (NLP).

Data Augmentation Machine Reading Comprehension +4


no code implementations EMNLP (sdp) 2020 Heng Zhang, Lifan Liu, Ruping Wang, Shaohu Hu, Shutian Ma, Chengzhi Zhang

Unlike the methods used in CL-SciSumm 2019, we construct inputs of models based on word vectors and add deep learning models for classification this year.

Sentence Similarity

One for All: Unified Workload Prediction for Dynamic Multi-tenant Edge Cloud Platforms

no code implementations2 Jun 2023 Shaoyuan Huang, Zheng Wang, Heng Zhang, Xiaofei Wang, Cheng Zhang, Wenyu Wang

In this paper, we propose an end-to-end framework with global pooling and static content awareness, DynEformer, to provide a unified workload prediction scheme for dynamic MT-ECP.

Time Series Prediction

Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attention

1 code implementation Tiny Papers @ ICLR 2023 Xiao Liu, Jian Zhang, Heng Zhang, Fuzhao Xue, Yang You

We evaluate our model on various dialogue understanding tasks including dialogue relation extraction, dialogue emotion recognition, and dialogue act classification.

Dialogue Act Classification Dialogue Understanding +2

Dynamical Equations With Bottom-up Self-Organizing Properties Learn Accurate Dynamical Hierarchies Without Any Loss Function

no code implementations4 Feb 2023 Danilo Vasconcellos Vargas, Tham Yik Foong, Heng Zhang

The hurdle is that general patterns are difficult to define in terms of dynamical equations and designing a system that could learn by reordering itself is still to be seen.

Modeling Video As Stochastic Processes for Fine-Grained Video Representation Learning

1 code implementation CVPR 2023 Heng Zhang, Daqing Liu, Qi Zheng, Bing Su

Specifically, we enforce the embeddings of the frame sequence of interest to approximate a goal-oriented stochastic process, i. e., Brownian bridge, in the latent space via a process-based contrastive loss.

Contrastive Learning Representation Learning +3

Adaptive incomplete multi-view learning via tensor graph completion

no code implementations7 Aug 2022 Heng Zhang, Xiaohong Chen

With the advancement of the data acquisition techniques, multi-view learning has become a hot topic.


Prediction-based Hybrid Slicing Framework for Service Level Agreement Guarantee in Mobility Scenarios: A Deep Learning Approach

no code implementations6 Aug 2022 Heng Zhang, Guangjin Pan, Shugong Xu, Shunqing Zhang, Zhiyuan Jiang

In the proposal, LSTM networks are employed to predict traffic demand and the location of each user in a slicing window level.

Joint Optimization of DNN Inference Delay and Energy under Accuracy Constraints for AR Applications

no code implementations3 Aug 2022 Guangjin Pan, Heng Zhang, Shugong Xu, Shunqing Zhang, Xiaojing Chen

The high computational complexity and high energy consumption of artificial intelligence (AI) algorithms hinder their application in augmented reality (AR) systems.

Edge-computing Scheduling

Characterizing the Program Expressive Power of Existential Rule Languages

no code implementations15 Dec 2021 Heng Zhang

Existential rule languages are a family of ontology languages that have been widely used in ontology-mediated query answering (OMQA).

Interest-based Item Representation Framework for Recommendation with Multi-Interests Capsule Network

no code implementations29 Sep 2021 Yanpeng Xie, Tong Zhang, Heng Zhang, Zhendong Qu

To make the framework model-agnostic, user Multi Interests Capsule Network is designed as an auxiliary task to jointly learn item-based item representations and interest-based item representations.

Recommendation Systems Representation Learning +1

DADgraph: A Discourse-aware Dialogue Graph Neural Network for Multiparty Dialogue Machine Reading Comprehension

no code implementations26 Apr 2021 Jiaqi Li, Ming Liu, Zihao Zheng, Heng Zhang, Bing Qin, Min-Yen Kan, Ting Liu

Multiparty Dialogue Machine Reading Comprehension (MRC) differs from traditional MRC as models must handle the complex dialogue discourse structure, previously unconsidered in traditional MRC.

Machine Reading Comprehension Question Answering

Using Full-text Content of Academic Articles to Build a Methodology Taxonomy of Information Science in China

no code implementations20 Jan 2021 Heng Zhang, Chengzhi Zhang

Accordingly, the research methodology entities were clustered and the basic methodology taxonomy was expanded using the clustering results to obtain a methodology taxonomy with more levels.

Chronological Citation Recommendation with Time Preference

no code implementations19 Jan 2021 Shutian Ma, Heng Zhang, Chengzhi Zhang, Xiaozhong Liu

Citation recommendation is an important task to assist scholars in finding candidate literature to cite.

Citation Recommendation

Localize to Classify and Classify to Localize: Mutual Guidance in Object Detection

1 code implementation29 Sep 2020 Heng Zhang, Elisa Fromont, Sébastien Lefevre, Bruno Avignon

Most deep learning object detectors are based on the anchor mechanism and resort to the Intersection over Union (IoU) between predefined anchor boxes and ground truth boxes to evaluate the matching quality between anchors and objects.

object-detection Object Detection

Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks

1 code implementation26 Sep 2020 Heng Zhang, Elisa Fromont, Sébastien Lefevre, Bruno Avignon

Multispectral images (e. g. visible and infrared) may be particularly useful when detecting objects with the same model in different environments (e. g. day/night outdoor scenes).

Multispectral Object Detection object-detection +1

Towards Universal Languages for Tractable Ontology Mediated Query Answering

no code implementations26 Nov 2019 Heng Zhang, Yan Zhang, Jia-Huai You, Zhiyong Feng, Guifei Jiang

On the negative side, we prove that there is, in general, no universal language for each of these families of languages.

Loop Restricted Existential Rules and First-order Rewritability for Query Answering

no code implementations19 Apr 2018 Vernon Asuncion, Yan Zhang, Heng Zhang, Yun Bai, Weisheng Si

In particular, we prove that this language satisfies the so-called bounded derivation-depth prop- erty (BDDP), which implies that the CQA is first-order rewritable, and its data complexity is in AC0 .

Hierarchical Multimodal Metric Learning for Multimodal Classification

no code implementations CVPR 2017 Heng Zhang, Vishal M. Patel, Rama Chellappa

The learned metrics can improve multimodal classification accuracy and experimental results on four datasets show that the proposed algorithm outperforms existing learning algorithms based on multiple metrics as well as other approaches tested on these datasets.

Classification General Classification +3

Expressive Completeness of Existential Rule Languages for Ontology-based Query Answering

no code implementations18 Apr 2016 Heng Zhang, Yan Zhang, Jia-Huai You

In this paper, we prove that disjunctive embedded dependencies exactly capture the class of recursively enumerable ontologies in Ontology-based Conjunctive Query Answering (OCQA).

Query Answering with Inconsistent Existential Rules under Stable Model Semantics

no code implementations18 Feb 2016 Hai Wan, Heng Zhang, Peng Xiao, Haoran Huang, Yan Zhang

Surprisingly, for R-acyclic existential rules with R-stratified or guarded existential rules with stratified negations, both the data complexity and combined complexity of query answering under the rule {repair semantics} remain the same as that under the conventional query answering semantics.

Expressiveness of Logic Programs under General Stable Model Semantics

no code implementations2 Dec 2014 Heng Zhang, Yan Zhang

The stable model semantics had been recently generalized to non-Herbrand structures by several works, which provides a unified framework and solid logical foundations for answer set programming.


Existential Rule Languages with Finite Chase: Complexity and Expressiveness

no code implementations19 Nov 2014 Heng Zhang, Yan Zhang, Jia-Huai You

Finite chase, or alternatively chase termination, is an important condition to ensure the decidability of existential rule languages.

Disjunctive Logic Programs versus Normal Logic Programs

no code implementations2 Apr 2013 Heng Zhang, Yan Zhang

This paper focuses on the expressive power of disjunctive and normal logic programs under the stable model semantics over finite, infinite, or arbitrary structures.


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