Search Results for author:
Found 57 papers, 19 papers with code
FedBIAD: Communication-Efficient and Accuracy-Guaranteed Federated Learning with Bayesian Inference-Based Adaptive Dropout
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.
A Latent Space Theory for Emergent Abilities in Large Language Models
Languages are not created randomly but rather to communicate information.
Towards Robust k-Nearest-Neighbor Machine Translation
Meanwhile we inject two types of perturbations into the retrieved pairs for robust training.
DavarOCR: A Toolbox for OCR and Multi-Modal Document Understanding
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.
Modeling dynamic volatility under uncertain environment with fuzziness and randomness
The problem related to predicting dynamic volatility in financial market plays a crucial role in many contexts.
Stochastic volatility modeling of high-frequency CSI 300 index and dynamic jump prediction driven by machine learning
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.
A Structure Self-Aware Model for Discourse Parsing on Multi-Party Dialogues
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
Exploring Dynamic Selection of Branch Expansion Orders for Code Generation
Due to the great potential in facilitating software development, code generation has attracted increasing attention recently.
Reciprocal Feature Learning via Explicit and Implicit Tasks in Scene Text Recognition
In this work, we excavate the implicit task, character counting within the traditional text recognition, without additional labor annotation cost.
Enhanced Aspect-Based Sentiment Analysis Models with Progressive Self-supervised Attention Learning
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)
Analysis of stock index with a generalized BN-S model: an approach based on machine learning and fuzzy parameters
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.
Match$^2$: A Matching over Matching Model for Similar Question Identification
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.
On Approximation Capabilities of ReLU Activation and Softmax Output Layer in Neural Networks
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.
Dual-FOFE-net Neural Models for Entity Linking with PageRank
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.
FreebaseQA: A New Factoid QA Data Set Matching Trivia-Style Question-Answer Pairs with Freebase
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.
Bandlimiting Neural Networks Against Adversarial Attacks
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.
Content based News Recommendation via Shortest Entity Distance over Knowledge Graphs
Content-based news recommendation systems need to recommend news articles based on the topics and content of articles without using user specific information.
Effective Context and Fragment Feature Usage for Named Entity Recognition
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.
A Multi-task Learning Approach for Named Entity Recognition using Local Detection
As a result, we observed competitive performance in nearly all of the tasks.
A General FOFE-net Framework for Simple and Effective Question Answering over Knowledge Bases
Question answering over knowledge base (KB-QA) has recently become a popular research topic in NLP.
Why Learning of Large-Scale Neural Networks Behaves Like Convex Optimization
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.
Fixed-Size Ordinally Forgetting Encoding Based Word Sense Disambiguation
In this paper, we present our method of using fixed-size ordinally forgetting encoding (FOFE) to solve the word sense disambiguation (WSD) problem.
A New Perspective on Machine Learning: How to do Perfect Supervised Learning
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.
DropFilter: A Novel Regularization Method for Learning Convolutional Neural Networks
Most of previous methods mainly consider to drop features from input data and hidden layers, such as Dropout, Cutout and DropBlocks.
Dual Fixed-Size Ordinally Forgetting Encoding (FOFE) for Competitive Neural Language Models
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.
Explicit Utilization of General Knowledge in Machine Reading Comprehension
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
The Lower The Simpler: Simplifying Hierarchical Recurrent Models
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.
Using Neural Network for Identifying Clickbaits in Online News Media
Online news media sometimes use misleading headlines to lure users to open the news article.
Accurate and Efficient Estimation of Small P-values with the Cross-Entropy Method: Applications in Genomic Data Analysis
$\textbf{Results:}$ We evaluate the performance of the proposed algorithm through simulations and demonstrate its application to three real-world examples in genomic studies.
Applications
Word Embeddings based on Fixed-Size Ordinally Forgetting Encoding
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.
Recurrent Neural Network-Based Sentence Encoder with Gated Attention for Natural Language Inference
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
P-splines with an $\ell_1$ penalty for repeated measures
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)
A Local Detection Approach for Named Entity Recognition and Mention Detection
In this paper, we study a novel approach for named entity recognition (NER) and mention detection (MD) in natural language processing.
Supervised Adversarial Networks for Image Saliency Detection
In the past few years, Generative Adversarial Network (GAN) became a prevalent research topic.
Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering
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
Commonsense Knowledge Enhanced Embeddings for Solving Pronoun Disambiguation Problems in Winograd Schema Challenge
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
Neural Networks Models for Entity Discovery and Linking
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.
A FOFE-based Local Detection Approach for Named Entity Recognition and Mention Detection
In this paper, we study a novel approach for named entity recognition (NER) and mention detection in natural language processing.
Distraction-Based Neural Networks for Document Summarization
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.
Enhanced LSTM for Natural Language Inference
Reasoning and inference are central to human and artificial intelligence.
Ranked #29 on
Natural Language Inference
on SNLI
Learning Convolutional Neural Networks using Hybrid Orthogonal Projection and Estimation
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.
Higher Order Recurrent Neural Networks
In this paper, we study novel neural network structures to better model long term dependency in sequential data.
Probabilistic Reasoning via Deep Learning: Neural Association Models
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
Part-of-Speech Relevance Weights for Learning Word Embeddings
The model proposed in this paper paper jointly optimizes word vectors and the POS relevance matrices.
Generating images with recurrent adversarial networks
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.
A Deep Learning Based Fast Image Saliency Detection Algorithm
In this paper, we propose a fast deep learning method for object saliency detection using convolutional neural networks.
Feedforward Sequential Memory Networks: A New Structure to Learn Long-term Dependency
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.
Feedforward Sequential Memory Neural Networks without Recurrent Feedback
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.
Leverage Financial News to Predict Stock Price Movements Using Word Embeddings and Deep Neural Networks
Financial news contains useful information on public companies and the market.
A Fixed-Size Encoding Method for Variable-Length Sequences with its Application to Neural Network Language Models
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.
Deep Learning for Object Saliency Detection and Image Segmentation
In this work, we use the computed saliency maps for image segmentation.
Hybrid Orthogonal Projection and Estimation (HOPE): A New Framework to Probe and Learn Neural Networks
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
