no code implementations • 14 Jul 2023 • Jingjing Xue, Min Liu, Sheng Sun, Yuwei Wang, Hui Jiang, Xuefeng Jiang
In this paper, we propose Federated learning with Bayesian Inference-based Adaptive Dropout (FedBIAD), which regards weight rows of local models as probability distributions and adaptively drops partial weight rows based on importance indicators correlated with the trend of local training loss.
no code implementations • 19 Apr 2023 • Hui Jiang
Languages are not created randomly but rather to communicate information.
3 code implementations • 17 Oct 2022 • Hui Jiang, Ziyao Lu, Fandong Meng, Chulun Zhou, Jie zhou, Degen Huang, Jinsong Su
Meanwhile we inject two types of perturbations into the retrieved pairs for robust training.
1 code implementation • 14 Jul 2022 • Liang Qiao, Hui Jiang, Ying Chen, Can Li, Pengfei Li, Zaisheng Li, Baorui Zou, Dashan Guo, Yingda Xu, Yunlu Xu, Zhanzhan Cheng, Yi Niu
Compared with the previous opensource OCR toolbox, DavarOCR has relatively more complete support for the sub-tasks of the cutting-edge technology of document understanding.
no code implementations • 27 Apr 2022 • Xianfei Hui, Baiqing Sun, Hui Jiang, Yan Zhou
The problem related to predicting dynamic volatility in financial market plays a crucial role in many contexts.
no code implementations • 6 Apr 2022 • Xianfei Hui, Baiqing Sun, Indranil SenGupta, Yan Zhou, Hui Jiang
This paper models stochastic process of price time series of CSI 300 index in Chinese financial market, analyzes volatility characteristics of intraday high-frequency price data.
1 code implementation • Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence 2021 • An-Hui Wang, Linfeng Song, Hui Jiang, Shaopeng Lai, Junfeng Yao, Min Zhang, Jinsong Su
Conversational discourse structures aim to describe how a dialogue is organised, thus they are helpful for dialogue understanding and response generation.
Ranked #3 on Discourse Parsing on STAC
1 code implementation • ACL 2021 • Hui Jiang, Chulun Zhou, Fandong Meng, Biao Zhang, Jie zhou, Degen Huang, Qingqiang Wu, Jinsong Su
Due to the great potential in facilitating software development, code generation has attracted increasing attention recently.
1 code implementation • 13 May 2021 • Hui Jiang, Yunlu Xu, Zhanzhan Cheng, ShiLiang Pu, Yi Niu, Wenqi Ren, Fei Wu, Wenming Tan
In this work, we excavate the implicit task, character counting within the traditional text recognition, without additional labor annotation cost.
1 code implementation • 5 Mar 2021 • Jinsong Su, Jialong Tang, Hui Jiang, Ziyao Lu, Yubin Ge, Linfeng Song, Deyi Xiong, Le Sun, Jiebo Luo
In aspect-based sentiment analysis (ABSA), many neural models are equipped with an attention mechanism to quantify the contribution of each context word to sentiment prediction.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA)
no code implementations • 22 Jan 2021 • Xianfei Hui, Baiqing Sun, Hui Jiang, Indranil SenGupta
In this paper we implement a combination of data-science and fuzzy theory to improve the classical Barndorff-Nielsen and Shephard model, and implement this to analyze the S&P 500 index.
no code implementations • 21 Jun 2020 • Zizhen Wang, Yixing Fan, Jiafeng Guo, Liu Yang, Ruqing Zhang, Yanyan Lan, Xue-Qi Cheng, Hui Jiang, Xiaozhao Wang
However, it has long been a challenge to properly measure the similarity between two questions due to the inherent variation of natural language, i. e., there could be different ways to ask a same question or different questions sharing similar expressions.
no code implementations • 10 Feb 2020 • Behnam Asadi, Hui Jiang
In this paper, we have extended the well-established universal approximator theory to neural networks that use the unbounded ReLU activation function and a nonlinear softmax output layer.
no code implementations • 30 Jul 2019 • Feng Wei, Uyen Trang Nguyen, Hui Jiang
Our neural linking models consist of three parts: a PageRank based candidate generation module, a dual-FOFE-net neural ranking model and a simple NIL entity clustering system.
1 code implementation • NAACL 2019 • Kelvin Jiang, Dekun Wu, Hui Jiang
In this paper, we present a new data set, named FreebaseQA, for open-domain factoid question answering (QA) tasks over structured knowledge bases, like Freebase.
no code implementations • ICLR 2020 • Yuping Lin, Kasra Ahmadi K. A., Hui Jiang
We first explicitly compute the Fourier transform of deep ReLU neural networks and show that there exist decaying but non-zero high frequency components in the Fourier spectrum of neural networks.
1 code implementation • 24 May 2019 • Kevin Joseph, Hui Jiang
Content-based news recommendation systems need to recommend news articles based on the topics and content of articles without using user specific information.
no code implementations • 5 Apr 2019 • Nargiza Nosirova, MingBin Xu, Hui Jiang
As a result, we observed competitive performance in nearly all of the tasks.
no code implementations • 5 Apr 2019 • Nargiza Nosirova, MingBin Xu, Hui Jiang
In this paper, we explore a new approach to named entity recognition (NER) with the goal of learning from context and fragment features more effectively, contributing to the improvement of overall recognition performance.
no code implementations • 29 Mar 2019 • Dekun Wu, Nana Nosirova, Hui Jiang, MingBin Xu
Question answering over knowledge base (KB-QA) has recently become a popular research topic in NLP.
no code implementations • 6 Mar 2019 • Hui Jiang
Furthermore, we have proved that gradient descent methods surely converge to a global minimum of zero loss provided that the disparity matrices maintain full rank.
no code implementations • 23 Feb 2019 • Xi Zhu, MingBin Xu, Hui Jiang
In this paper, we present our method of using fixed-size ordinally forgetting encoding (FOFE) to solve the word sense disambiguation (WSD) problem.
no code implementations • 7 Jan 2019 • Hui Jiang
In this work, we introduce the concept of bandlimiting into the theory of machine learning because all physical processes are bandlimited by nature, including real-world machine learning tasks.
no code implementations • 16 Nov 2018 • Hengyue Pan, Hui Jiang, Xin Niu, Yong Dou
Most of previous methods mainly consider to drop features from input data and hidden layers, such as Dropout, Cutout and DropBlocks.
no code implementations • EMNLP 2018 • Sedtawut Watcharawittayakul, MingBin Xu, Hui Jiang
In this paper, we propose a new approach to employ the fixed-size ordinally-forgetting encoding (FOFE) (Zhang et al., 2015b) in neural languages modelling, called dual-FOFE.
no code implementations • ACL 2019 • Chao Wang, Hui Jiang
To bridge the gap between Machine Reading Comprehension (MRC) models and human beings, which is mainly reflected in the hunger for data and the robustness to noise, in this paper, we explore how to integrate the neural networks of MRC models with the general knowledge of human beings.
Ranked #23 on Question Answering on SQuAD1.1 dev
no code implementations • NAACL 2019 • Chao Wang, Hui Jiang
To improve the training efficiency of hierarchical recurrent models without compromising their performance, we propose a strategy named as `the lower the simpler', which is to simplify the baseline models by making the lower layers simpler than the upper layers.
2 code implementations • 20 Jun 2018 • Amin Omidvar, Hui Jiang, Aijun An
Online news media sometimes use misleading headlines to lure users to open the news article.
1 code implementation • 9 Mar 2018 • Yang Shi, Mengqiao Wang, Weiping Shi, Ji-Hyun Lee, Huining Kang, Hui Jiang
$\textbf{Results:}$ We evaluate the performance of the proposed algorithm through simulations and demonstrate its application to three real-world examples in genomic studies.
Applications
no code implementations • EMNLP 2017 • Joseph Sanu, MingBin Xu, Hui Jiang, Quan Liu
In this paper, we propose to learn word embeddings based on the recent fixed-size ordinally forgetting encoding (FOFE) method, which can almost uniquely encode any variable-length sequence into a fixed-size representation.
2 code implementations • WS 2017 • Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Si Wei, Hui Jiang, Diana Inkpen
The RepEval 2017 Shared Task aims to evaluate natural language understanding models for sentence representation, in which a sentence is represented as a fixed-length vector with neural networks and the quality of the representation is tested with a natural language inference task.
Ranked #70 on Natural Language Inference on SNLI
Natural Language Inference Natural Language Understanding +1
1 code implementation • 27 Jul 2017 • Brian D. Segal, Michael R. Elliott, Thomas Braun, Hui Jiang
In addition to $\ell_2$ penalties, $\ell_1$-type penalties have been used in nonparametric and semiparametric regression to achieve greater flexibility, such as in locally adaptive regression splines, $\ell_1$ trend filtering, and the fused lasso additive model.
Methodology 62G08 (Primary), 62P10 (Secondary)
no code implementations • ACL 2017 • Mingbin Xu, Hui Jiang, Sedtawut Watcharawittayakul
In this paper, we study a novel approach for named entity recognition (NER) and mention detection (MD) in natural language processing.
no code implementations • 24 Apr 2017 • Hengyue Pan, Hui Jiang
In the past few years, Generative Adversarial Network (GAN) became a prevalent research topic.
no code implementations • 14 Mar 2017 • Junbei Zhang, Xiaodan Zhu, Qian Chen, Li-Rong Dai, Si Wei, Hui Jiang
The last several years have seen intensive interest in exploring neural-network-based models for machine comprehension (MC) and question answering (QA).
Ranked #39 on Question Answering on SQuAD1.1 dev
no code implementations • 13 Nov 2016 • Quan Liu, Hui Jiang, Zhen-Hua Ling, Xiaodan Zhu, Si Wei, Yu Hu
The PDP task we investigate in this paper is a complex coreference resolution task which requires the utilization of commonsense knowledge.
Ranked #63 on Coreference Resolution on Winograd Schema Challenge
no code implementations • 11 Nov 2016 • Dan Liu, Wei. Lin, Shiliang Zhang, Si Wei, Hui Jiang
This paper describes the USTC_NELSLIP systems submitted to the Trilingual Entity Detection and Linking (EDL) track in 2016 TAC Knowledge Base Population (KBP) contests.
1 code implementation • 2 Nov 2016 • Mingbin Xu, Hui Jiang
In this paper, we study a novel approach for named entity recognition (NER) and mention detection in natural language processing.
1 code implementation • 26 Oct 2016 • Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Si Wei, Hui Jiang
Distributed representation learned with neural networks has recently shown to be effective in modeling natural languages at fine granularities such as words, phrases, and even sentences.
11 code implementations • ACL 2017 • Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Si Wei, Hui Jiang, Diana Inkpen
Reasoning and inference are central to human and artificial intelligence.
Ranked #29 on Natural Language Inference on SNLI
1 code implementation • 20 Jun 2016 • Hengyue Pan, Hui Jiang
Convolutional neural networks (CNNs) have yielded the excellent performance in a variety of computer vision tasks, where CNNs typically adopt a similar structure consisting of convolution layers, pooling layers and fully connected layers.
no code implementations • 30 Apr 2016 • Rohollah Soltani, Hui Jiang
In this paper, we study novel neural network structures to better model long term dependency in sequential data.
no code implementations • 24 Mar 2016 • Quan Liu, Zhen-Hua Ling, Hui Jiang, Yu Hu
The model proposed in this paper paper jointly optimizes word vectors and the POS relevance matrices.
no code implementations • 24 Mar 2016 • Quan Liu, Hui Jiang, Andrew Evdokimov, Zhen-Hua Ling, Xiaodan Zhu, Si Wei, Yu Hu
We propose to use neural networks to model association between any two events in a domain.
Ranked #11 on Natural Language Understanding on PDP60
Natural Language Inference Natural Language Understanding +2
1 code implementation • 16 Feb 2016 • Daniel Jiwoong Im, Chris Dongjoo Kim, Hui Jiang, Roland Memisevic
Gatys et al. (2015) showed that optimizing pixels to match features in a convolutional network with respect reference image features is a way to render images of high visual quality.
no code implementations • 1 Feb 2016 • Hengyue Pan, Hui Jiang
In this paper, we propose a fast deep learning method for object saliency detection using convolutional neural networks.
no code implementations • 28 Dec 2015 • Shiliang Zhang, Cong Liu, Hui Jiang, Si Wei, Li-Rong Dai, Yu Hu
In this paper, we propose a novel neural network structure, namely \emph{feedforward sequential memory networks (FSMN)}, to model long-term dependency in time series without using recurrent feedback.
no code implementations • 9 Oct 2015 • ShiLiang Zhang, Hui Jiang, Si Wei, Li-Rong Dai
We introduce a new structure for memory neural networks, called feedforward sequential memory networks (FSMN), which can learn long-term dependency without using recurrent feedback.
no code implementations • NAACL 2016 • Yangtuo Peng, Hui Jiang
Financial news contains useful information on public companies and the market.
1 code implementation • 6 May 2015 • Shiliang Zhang, Hui Jiang, MingBin Xu, JunFeng Hou, Li-Rong Dai
In this paper, we propose the new fixed-size ordinally-forgetting encoding (FOFE) method, which can almost uniquely encode any variable-length sequence of words into a fixed-size representation.
no code implementations • 5 May 2015 • Hengyue Pan, Bo wang, Hui Jiang
In this work, we use the computed saliency maps for image segmentation.
no code implementations • 3 Feb 2015 • Shiliang Zhang, Hui Jiang
As a result, the HOPE framework can be used as a novel tool to probe why and how NNs work, more importantly, to learn NNs in either supervised or unsupervised ways.
Ranked #23 on Image Classification on MNIST