Related papers: Efficient learning strategy of Chinese characters …

Chinese discourse coherence modeling remains a challenge taskin Natural Language Processing field.Existing approaches mostlyfocus on the need for feature engineering, whichadoptthe sophisticated features to capture the logic or syntactic or…

Automatic font generation remains a challenging research issue, primarily due to the vast number of Chinese characters, each with unique and intricate structures. Our investigation of previous studies reveals inherent bias capable of…

Unlike theoretical distributed learning (DL), DL over wireless edge networks faces the inherent dynamics/uncertainty of wireless connections and edge nodes, making DL less efficient or even inapplicable under the highly dynamic wireless…

Chinese word segmentation (CWS) is the basic of Chinese natural language processing (NLP). The quality of word segmentation will directly affect the rest of NLP tasks. Recently, with the artificial intelligence tide rising again, Long…

Representation learning is the foundation of machine reading comprehension and inference. In state-of-the-art models, character-level representations have been broadly adopted to alleviate the problem of effectively representing rare or…

Despite the simplicity, stochastic gradient descent (SGD)-like algorithms are successful in training deep neural networks (DNNs). Among various attempts to improve SGD, weight averaging (WA), which averages the weights of multiple models,…

Deep convolutional neural network (DCNN) based supervised learning is a widely practiced approach for large-scale image classification. However, retraining these large networks to accommodate new, previously unseen data demands high…

Most previous approaches to Chinese word segmentation formalize this problem as a character-based sequence labeling task where only contextual information within fixed sized local windows and simple interactions between adjacent tags can be…

This paper studies graph-based active learning, where the goal is to reconstruct a binary signal defined on the nodes of a weighted graph, by sampling it on a small subset of the nodes. A new sampling algorithm is proposed, which…

Using the requisition papers of Chinese Nature Science Basic Research in management and information department, we construct the weighted network of research areas({\bf WRAN}) represented by the subject codes. In WRAN, two research areas…

This paper presents an investigation of several techniques that increase the accuracy of online handwritten Chinese character recognition (HCCR). We propose a new training strategy named DropDistortion to train a deep convolutional neural…

Convolutional neural networks (CNNs) have constantly achieved better performance over years by introducing more complex topology, and enlarging the capacity towards deeper and wider CNNs. This makes the manual design of CNNs extremely…

Recurrence networks are powerful tools used effectively in the nonlinear analysis of time series data. The analysis in this context is done mostly with unweighted and undirected complex networks constructed with specific criteria from the…

Recently, there have been increasing demands to construct compact deep architectures to remove unnecessary redundancy and to improve the inference speed. While many recent works focus on reducing the redundancy by eliminating unneeded…

Standard neural networks struggle to generalize under distribution shifts in computer vision. Fortunately, combining multiple networks can consistently improve out-of-distribution generalization. In particular, weight averaging (WA)…

Neural network models have been proposed to explain the grapheme-phoneme mapping process in humans for many alphabet languages. These models not only successfully learned the correspondence of the letter strings and their pronunciation, but…

Approaches to continual learning aim to successfully learn a set of related tasks that arrive in an online manner. Recently, several frameworks have been developed which enable deep learning to be deployed in this learning scenario. A key…

Dictionary learning is a cornerstone of image classification. We set out to address a longstanding challenge in using dictionary learning for classification; that is to simultaneously maximise the discriminability and…

Network node embedding is an active research subfield of complex network analysis. This paper contributes a novel approach to learning network node embeddings and direct node classification using a node ranking scheme coupled with an…

Recent advances in large-scale language representation models such as BERT have improved the state-of-the-art performances in many NLP tasks. Meanwhile, character-level Chinese NLP models, including BERT for Chinese, have also demonstrated…