no code implementations • EMNLP 2021 • Sheng Zhang, Xin Zhang, Weiming Zhang, Anders Søgaard
Using data from English cloze tests, in which subjects also self-reported their gender, age, education, and race, we examine performance differences of pretrained language models across demographic groups, defined by these (protected) attributes.
no code implementations • 22 Apr 2022 • Sheng Zhang, Jin Wang, Haitao Jiang, Rui Song
Some feature attribution methods have shown promising results in computer vision, especially the gradient-based methods where effectively smoothing the gradients with reference data is key to a robust and faithful result.
no code implementations • 12 Apr 2022 • Yi-Hsuan Liu, Sheng Zhang, Puhan Zhang, Ting-Kuo Lee, Gia-Wei Chern
We present a scalable machine learning (ML) model to predict local electronic properties such as on-site electron number and double occupation for disordered correlated electron systems.
1 code implementation • ACL 2022 • Miryam de Lhoneux, Sheng Zhang, Anders Søgaard
Large multilingual pretrained language models such as mBERT and XLM-RoBERTa have been found to be surprisingly effective for cross-lingual transfer of syntactic parsing models (Wu and Dredze 2019), but only between related languages.
1 code implementation • ACL 2022 • Ilias Chalkidis, Tommaso Pasini, Sheng Zhang, Letizia Tomada, Sebastian Felix Schwemer, Anders Søgaard
We present a benchmark suite of four datasets for evaluating the fairness of pre-trained language models and the techniques used to fine-tune them for downstream tasks.
no code implementations • 21 Feb 2022 • Lihan Chen, Sihang Jiang, Jingping Liu, Chao Wang, Sheng Zhang, Chenhao Xie, Jiaqing Liang, Yanghua Xiao, Rui Song
Knowledge graphs (KGs) are an important source repository for a wide range of applications and rule mining from KGs recently attracts wide research interest in the KG-related research community.
no code implementations • 3 Jan 2022 • Puhan Zhang, Sheng Zhang, Gia-Wei Chern
A general theory of the descriptor for the classical fields is formulated, and two types of models are distinguished depending on the presence or absence of an internal symmetry for the classical field.
no code implementations • 15 Dec 2021 • Sheng Zhang, Hao Cheng, Shikhar Vashishth, Cliff Wong, Jinfeng Xiao, Xiaodong Liu, Tristan Naumann, Jianfeng Gao, Hoifung Poon
Zero-shot entity linking has emerged as a promising direction for generalizing to new entities, but it still requires example gold entity mentions during training and canonical descriptions for all entities, both of which are rarely available outside of Wikipedia.
no code implementations • 9 Dec 2021 • Yongbiao Chen, Sheng Zhang, Fangxin Liu, Chenggang Wu, Kaicheng Guo, Zhengwei Qi
Specifically, we directly constrain the output from the convolutional neural network to be discrete binary codes and ensure the learned binary codes are optimal for classification.
no code implementations • NeurIPS 2021 • Sheng Zhang, Zhe Zhang, Siva Theja Maguluri
The focus of this paper is on sample complexity guarantees of average-reward reinforcement learning algorithms, which are known to be more challenging to study than their discounted-reward counterparts.
no code implementations • 27 Nov 2021 • Jianian Wang, Sheng Zhang, Yanghua Xiao, Rui Song
With multiple components and relations, financial data are often presented as graph data, since it could represent both the individual features and the complicated relations.
no code implementations • 22 Nov 2021 • Jing Fan, Xin Zhang, Sheng Zhang, Yan Pan, Lixiang Guo
In light of the success of transferring language models into NLP tasks, we ask whether the full BERT model is always the best and does it exist a simple but effective method to find the winning ticket in state-of-the-art deep neural networks without complex calculations.
no code implementations • EMNLP 2021 • Sheng Zhang, Cliff Wong, Naoto Usuyama, Sarthak Jain, Tristan Naumann, Hoifung Poon
Extracting relations across large text spans has been relatively underexplored in NLP, but it is particularly important for high-value domains such as biomedicine, where obtaining high recall of the latest findings is crucial for practical applications.
no code implementations • 27 Jul 2021 • Jie Li, Sheng Zhang, Kai Han, Xia Yuan, Chunxia Zhao, Yu Liu
UGV-KPNet is computationally efficient with a small number of parameters and provides pixel-level accurate keypoints detection results in real-time.
2 code implementations • 11 Jun 2021 • Daochen Zha, Jingru Xie, Wenye Ma, Sheng Zhang, Xiangru Lian, Xia Hu, Ji Liu
Games are abstractions of the real world, where artificial agents learn to compete and cooperate with other agents.
no code implementations • 27 May 2021 • Runzhe Wan, Sheng Zhang, Chengchun Shi, Shikai Luo, Rui Song
Order dispatch is one of the central problems to ride-sharing platforms.
no code implementations • 27 May 2021 • Sheng Zhang, Puhan Zhang, Gia-Wei Chern
With the aid of modern machine learning methods, we demonstrate the first-ever large-scale kinetic Monte Carlo simulations of the phase separation process for the Falicov-Kimball model, which is one of the canonical strongly correlated electron systems.
no code implementations • 5 May 2021 • Yongbiao Chen, Sheng Zhang, Fangxin Liu, Zhigang Chang, Mang Ye, Zhengwei Qi
Until now, the deep hashing for the image retrieval community has been dominated by convolutional neural network architectures, e. g. \texttt{Resnet}\cite{he2016deep}.
1 code implementation • 12 Apr 2021 • Elias Stengel-Eskin, Kenton Murray, Sheng Zhang, Aaron Steven White, Benjamin Van Durme
While numerous attempts have been made to jointly parse syntax and semantics, high performance in one domain typically comes at the price of performance in the other.
no code implementations • 11 Feb 2021 • Jiahao Xie, Sheng Zhang, Jianwei Lu, Ye Luo
Coarse-to-fine models and cascade segmentation architectures are widely adopted to solve the problem of large scale variations in medical image segmentation.
no code implementations • 21 Jan 2021 • Yunfei Pu, Sheng Zhang, Yukai Wu, Nan Jiang, Wei Chang, Chang Li, Luming Duan
The experimental realization of entanglement connection of two quantum repeater segments with an efficient memory-enhanced scaling demonstrates a key advantage of the quantum repeater protocol, which makes a cornerstone towards future large-scale quantum networks.
Quantum Physics
no code implementations • 21 Jan 2021 • Sheng Zhang
The main result is a submetric characterization of the class of Banach spaces admitting an equivalent norm with Rolewicz's property ($\beta$).
Functional Analysis
no code implementations • 1 Jan 2021 • Sheng Zhang, Rui Song, Wenbin Lu
In a number of experiments on benchmark datasets, we show that the proposed GraphCGAN outperforms the baseline methods by a significant margin.
1 code implementation • EMNLP 2020 • Ye Liu, Sheng Zhang, Rui Song, Suo Feng, Yanghua Xiao
Effectively filtering out noisy articles as well as bad answers is the key to improving extraction accuracy.
1 code implementation • 23 Sep 2020 • Sheng Zhang, Xin Zhang, Weiming Zhang, Anders Søgaard
Multi-task transfer learning based on pre-trained language encoders achieves state-of-the-art performance across a range of tasks.
no code implementations • 3 Sep 2020 • Sheng Zhang, Xiu Yang, Samy Tindel, Guang Lin
We prove that under certain conditions, the observable and its derivatives of any order are governed by a single Gaussian random field, which is the aforementioned AGRF.
Statistics Theory Probability Statistics Theory
20 code implementations • 12 May 2020 • Ivan Perov, Daiheng Gao, Nikolay Chervoniy, Kunlin Liu, Sugasa Marangonda, Chris Umé, Mr. Dpfks, Carl Shift Facenheim, Luis RP, Jian Jiang, Sheng Zhang, Pingyu Wu, Bo Zhou, Weiming Zhang
Deepfake defense not only requires the research of detection but also requires the efforts of generation methods.
Ranked #1 on
Face Swapping
on FaceForensics++
no code implementations • WS 2019 • Simon Ostermann, Sheng Zhang, Michael Roth, Peter Clark
This paper reports on the results of the shared tasks of the COIN workshop at EMNLP-IJCNLP 2019.
no code implementations • ACL 2020 • Elias Stengel-Eskin, Aaron Steven White, Sheng Zhang, Benjamin Van Durme
We introduce a transductive model for parsing into Universal Decompositional Semantics (UDS) representations, which jointly learns to map natural language utterances into UDS graph structures and annotate the graph with decompositional semantic attribute scores.
1 code implementation • LREC 2020 • Aaron Steven White, Elias Stengel-Eskin, Siddharth Vashishtha, Venkata Govindarajan, Dee Ann Reisinger, Tim Vieira, Keisuke Sakaguchi, Sheng Zhang, Francis Ferraro, Rachel Rudinger, Kyle Rawlins, Benjamin Van Durme
We present the Universal Decompositional Semantics (UDS) dataset (v1. 0), which is bundled with the Decomp toolkit (v0. 1).
no code implementations • IJCNLP 2019 • Sheng Zhang, Xutai Ma, Kevin Duh, Benjamin Van Durme
We unify different broad-coverage semantic parsing tasks under a transduction paradigm, and propose an attention-based neural framework that incrementally builds a meaning representation via a sequence of semantic relations.
Ranked #2 on
UCCA Parsing
on SemEval 2019 Task 1
no code implementations • 5 Sep 2019 • Chang Li, Nan Jiang, Yukai Wu, Wei Chang, Yunfei Pu, Sheng Zhang, Lu-Ming Duan
The use of multiplexed atomic quantum memories (MAQM) can significantly enhance the efficiency to establish entanglement in a quantum network.
Quantum Physics
no code implementations • 17 Jul 2019 • Sheng Zhang, Guang Lin
We demonstrate how to use our algorithm step by step and compare our algorithm with threshold sparse Bayesian regression (TSBR) for the discovery of differential equations.
no code implementations • 2 Jul 2019 • Shanshan Liu, Xin Zhang, Sheng Zhang, Hui Wang, Weiming Zhang
Machine reading comprehension (MRC), which requires a machine to answer questions based on a given context, has attracted increasing attention with the incorporation of various deep-learning techniques over the past few years.
1 code implementation • 6 Jun 2019 • Yuliang Liu, Sheng Zhang, Lianwen Jin, Lele Xie, Yaqiang Wu, Zhepeng Wang
Scene text in the wild is commonly presented with high variant characteristics.
Ranked #1 on
Scene Text Detection
on IC19-ReCTs
(using extra training data)
no code implementations • 27 May 2019 • Zaiwei Chen, Sheng Zhang, Thinh T. Doan, John-Paul Clarke, Siva Theja Maguluri
To demonstrate the generality of our theoretical results on Markovian SA, we use it to derive the finite-sample bounds of the popular $Q$-learning with linear function approximation algorithm, under a condition on the behavior policy.
1 code implementation • ACL 2019 • Sheng Zhang, Xutai Ma, Kevin Duh, Benjamin Van Durme
Our experimental results outperform all previously reported SMATCH scores, on both AMR 2. 0 (76. 3% F1 on LDC2017T10) and AMR 1. 0 (70. 2% F1 on LDC2014T12).
Ranked #1 on
AMR Parsing
on LDC2014T12:
no code implementations • NAACL 2019 • Shuohang Wang, Sheng Zhang, Yelong Shen, Xiaodong Liu, Jingjing Liu, Jianfeng Gao, Jing Jiang
Commonsense reasoning is fundamental to natural language understanding.
Ranked #3 on
Natural Language Understanding
on PDP60
no code implementations • 20 Nov 2018 • Chao Chen, Sheng Zhang, Cuibing Du
Change detection has been a challenging visual task due to the dynamic nature of real-world scenes.
no code implementations • 30 Oct 2018 • Sheng Zhang, Xiaodong Liu, Jingjing Liu, Jianfeng Gao, Kevin Duh, Benjamin Van Durme
We present a large-scale dataset, ReCoRD, for machine reading comprehension requiring commonsense reasoning.
no code implementations • EMNLP 2018 • Sheng Zhang, Xutai Ma, Rachel Rudinger, Kevin Duh, Benjamin Van Durme
We introduce the task of cross-lingual decompositional semantic parsing: mapping content provided in a source language into a decompositional semantic analysis based on a target language.
no code implementations • WS 2018 • Kaiyin Zhou, Sheng Zhang, Xiangyu Meng, Qi Luo, Yuxing Wang, Ke Ding, Yukun Feng, Mo Chen, Kevin Cohen, Jingbo Xia
Sequence labeling of biomedical entities, e. g., side effects or phenotypes, was a long-term task in BioNLP and MedNLP communities.
no code implementations • SEMEVAL 2018 • Hongyuan Mei, Sheng Zhang, Kevin Duh, Benjamin Van Durme
Cross-lingual information extraction (CLIE) is an important and challenging task, especially in low resource scenarios.
1 code implementation • SEMEVAL 2018 • Sheng Zhang, Kevin Duh, Benjamin Van Durme
Fine-grained entity typing is the task of assigning fine-grained semantic types to entity mentions.
no code implementations • 21 Apr 2018 • Sheng Zhang, Kevin Duh, Benjamin Van Durme
We introduce the task of cross-lingual semantic parsing: mapping content provided in a source language into a meaning representation based on a target language.
1 code implementation • EMNLP 2018 • Rachel Rudinger, Adam Teichert, Ryan Culkin, Sheng Zhang, Benjamin Van Durme
We present a model for semantic proto-role labeling (SPRL) using an adapted bidirectional LSTM encoding strategy that we call "Neural-Davidsonian": predicate-argument structure is represented as pairs of hidden states corresponding to predicate and argument head tokens of the input sequence.
no code implementations • 28 Mar 2018 • Yuechao Gao, Nianhong Liu, Sheng Zhang
It is a challenging task to deploy computationally and memory intensive State-of-the-art deep neural networks (DNNs) on embedded systems with limited hardware resources and power budgets.
1 code implementation • 23 Jan 2018 • Yuechao Gao, Nianhong Liu, Sheng Zhang
To address memory and computation resource limitations for hardware-oriented acceleration of deep convolutional neural networks (CNNs), we present a computation flow, stacked filters stationary flow (SFS), and a corresponding data encoding format, relative indexed compressed sparse filter format (CSF), to make the best of data sparsity, and simplify data handling at execution time.
no code implementations • 2 Jan 2018 • Jiashu Zhang, Sheng Zhang, Defang Li
Over the last decade, both the neural network and kernel adaptive filter have successfully been used for nonlinear signal processing.
no code implementations • 12 Nov 2017 • Sheng Zhang, Yuliang Liu, Lianwen Jin, Canjie Luo
In this paper, we propose a refined scene text detector with a \textit{novel} Feature Enhancement Network (FEN) for Region Proposal and Text Detection Refinement.
no code implementations • IJCNLP 2017 • Sheng Zhang, Kevin Duh, Benjamin Van Durme
Cross-lingual open information extraction is the task of distilling facts from the source language into representations in the target language.
no code implementations • SEMEVAL 2017 • Sheng Zhang, Jiajun Cheng, Hui Wang, Xin Zhang, Pei Li, Zhaoyun Ding
We describes deep neural networks frameworks in this paper to address the community question answering (cQA) ranking task (SemEval-2017 task 3).
no code implementations • EACL 2017 • Sheng Zhang, Kevin Duh, Benjamin Van Durme
Conventional pipeline solutions decompose the task as machine translation followed by information extraction (or vice versa).
3 code implementations • WS 2019 • Adrian Benton, Huda Khayrallah, Biman Gujral, Dee Ann Reisinger, Sheng Zhang, Raman Arora
We present Deep Generalized Canonical Correlation Analysis (DGCCA) -- a method for learning nonlinear transformations of arbitrarily many views of data, such that the resulting transformations are maximally informative of each other.
no code implementations • TACL 2017 • Sheng Zhang, Rachel Rudinger, Kevin Duh, Benjamin Van Durme
Humans have the capacity to draw common-sense inferences from natural language: various things that are likely but not certain to hold based on established discourse, and are rarely stated explicitly.
no code implementations • 7 Jun 2015 • Yi-Lun Wang, Sheng Zhang, Junjie Zheng, Heng Chen, Huafu Chen
In this paper, we focus on how to locate the relevant or discriminative brain regions related with external stimulus or certain mental decease, which is also called support identification, based on the neuroimaging data.
1 code implementation • 12 Feb 2015 • Sheng Zhang, Brendan Harding
We established a new method called Discrete Weierstrass Fourier Transform, a faster and more generalized Discrete Fourier Transform, to approximate discrete data.
Numerical Analysis
no code implementations • 17 Oct 2014 • Yi-Lun Wang, Junjie Zheng, Sheng Zhang, Xujun Duan, Huafu Chen
In this paper, we consider voxel selection for functional Magnetic Resonance Imaging (fMRI) brain data with the aim of finding a more complete set of probably correlated discriminative voxels, thus improving interpretation of the discovered potential biomarkers.