For the correction subtask, we utilize the masked language model, the seq2seq model and the spelling check model to generate corrections based on the detection results.
We have accumulated 1, 119 error templates for Chinese GEC based on this method.
Nonnegative matrix factorization (NMF) has been widely used to dimensionality reduction in machine learning.
In addition, we conducted an ablation experiment and an interchangeability experiment to verify the ability and interchangeability of the three channels.
Cervical cytopathology image classification is an important method to diagnose cervical cancer.
In this paper, we develop a bottom-level Transistor Operations (TOs) method to expose the role of activation functions and neural network structure in energy consumption scaling with DL model configuration.
Ensemble learning is a way to improve the accuracy of algorithms, and finding multiple learning models with complementarity types is the basis of ensemble learning.
The gold standard for gastric cancer detection is gastric histopathological image analysis, but there are certain drawbacks in the existing histopathological detection and diagnosis.
The Matrix-based Renyi's entropy enables us to directly measure information quantities from given data without the costly probability density estimation of underlying distributions, thus has been widely adopted in numerous statistical learning and inference tasks.
This paper presents MuCGEC, a multi-reference multi-source evaluation dataset for Chinese Grammatical Error Correction (CGEC), consisting of 7, 063 sentences collected from three Chinese-as-a-Second-Language (CSL) learner sources.
Traditional nonnegative matrix factorization (NMF) learns a new feature representation on the whole data space, which means treating all features equally.
The detection of tiny objects in microscopic videos is a problematic point, especially in large-scale experiments.
Method: This paper proposes a deep ensemble model based on image-level labels for the binary classification of benign and malignant lesions of breast histopathological images.
Experimental result shows that the proposed PID-Net has the best performance and potential for dense tiny objects counting tasks, which achieves 96. 97% counting accuracy on the dataset with 2448 yeast cell images.
Despite the striking performance achieved by modern detectors when training and test data are sampled from the same or similar distribution, the generalization ability of detectors under unknown distribution shifts remains hardly studied.
This study has high research significance and application value, which can be referred to microbial researchers to have a comprehensive understanding of microorganism biovolume measurements using digital image analysis methods and potential applications.
Traditional machine learning methods achieve maximum accuracy of 76. 02% and deep learning method achieves a maximum accuracy of 95. 37%.
The various works related to Computer Assisted Sperm Analysis methods in the last 30 years (since 1988) are comprehensively introduced and analysed in this survey.
Image analysis technology is used to solve the inadvertences of artificial traditional methods in disease, wastewater treatment, environmental change monitoring analysis and convolutional neural networks (CNN) play an important role in microscopic image analysis.
In the past ten years, the computing power of machine vision (MV) has been continuously improved, and image analysis algorithms have developed rapidly.
no code implementations • 19 Jan 2022 • Joshua T. Vogelstein, Timothy Verstynen, Konrad P. Kording, Leyla Isik, John W. Krakauer, Ralph Etienne-Cummings, Elizabeth L. Ogburn, Carey E. Priebe, Randal Burns, Kwame Kutten, James J. Knierim, James B. Potash, Thomas Hartung, Lena Smirnova, Paul Worley, Alena Savonenko, Ian Phillips, Michael I. Miller, Rene Vidal, Jeremias Sulam, Adam Charles, Noah J. Cowan, Maxim Bichuch, Archana Venkataraman, Chen Li, Nitish Thakor, Justus M Kebschull, Marilyn Albert, Jinchong Xu, Marshall Hussain Shuler, Brian Caffo, Tilak Ratnanather, Ali Geisa, Seung-Eon Roh, Eva Yezerets, Meghana Madhyastha, Javier J. How, Tyler M. Tomita, Jayanta Dey, Ningyuan, Huang, Jong M. Shin, Kaleab Alemayehu Kinfu, Pratik Chaudhari, Ben Baker, Anna Schapiro, Dinesh Jayaraman, Eric Eaton, Michael Platt, Lyle Ungar, Leila Wehbe, Adam Kepecs, Amy Christensen, Onyema Osuagwu, Bing Brunton, Brett Mensh, Alysson R. Muotri, Gabriel Silva, Francesca Puppo, Florian Engert, Elizabeth Hillman, Julia Brown, Chris White, Weiwei Yang
We call this 'retrospective learning'.
We first theoretically investigate how the weight coupling problem affects the network searching performance from a parameter distribution perspective, and then propose a novel supernet training strategy with a Distribution Consistent Constraint that can provide a good measurement for the extent to which two architectures can share weights.
In this paper, we propose a novel algorithm to compute the Wasserstein-p distance between discrete measures by restricting the optimal transport (OT) problem on a subset.
Video inpainting remains a challenging problem to fill with plausible and coherent content in unknown areas in video frames despite the prevalence of data-driven methods.
Each type of EM contains 40 original and 40 GT images, in total 1680 EM images.
Our results show that the Markov dependence impacts on the generalization error in the way that sample size would be discounted by a multiplicative factor depending on the spectral gap of underlying Markov chain.
However, the development of such an automated method requires a large amount of data with precisely annotated masks which is hard to obtain.
However, there is still a lack of an open and universal digital pathology platform to assist doctors in the management and analysis of digital pathological sections, as well as the management and structured description of relevant patient information.
In order to take advantage of segmentation methods based on point annotation, further alleviate the manual workload, and make cancer diagnosis more efficient and accurate, it is necessary to develop an automatic nucleus detection algorithm, which can automatically and efficiently locate the position of the nucleus in the pathological image and extract valuable information for pathologists.
To address this issue, we propose Biomedical Information Extraction, a hybrid neural network to extract relations from biomedical text and unstructured medical reports.
In this study, we propose a framework that combines pathological images and medical reports to generate a personalized diagnosis result for individual patient.
Tumor region detection, subtype and grade classification are the fundamental diagnostic indicators for renal cell carcinoma (RCC) in whole-slide images (WSIs).
Adverse media or negative news screening is crucial for the identification of such non-financial risks.
Previous works on key information extraction from visually rich documents (VRDs) mainly focus on labeling the text within each bounding box (i. e., semantic entity), while the relations in-between are largely unexplored.
Ranked #1 on Entity Linking on FUNSD
no code implementations • 11 Oct 2021 • Hechen Yang, Chen Li, Xin Zhao, Bencheng Cai, Jiawei Zhang, Pingli Ma, Peng Zhao, Ao Chen, Hongzan Sun, Yueyang Teng, Shouliang Qi, Tao Jiang, Marcin Grzegorzek
The Environmental Microorganism Image Dataset Seventh Version (EMDS-7) is a microscopic image data set, including the original Environmental Microorganism images (EMs) and the corresponding object labeling files in ". XML" format file.
We believe that this approach of exploiting general data distribution knowledge form neural networks can be applied to a wide range of scarce data open challenges.
Semantic segmentation has been continuously investigated in the last ten years, and majority of the established technologies are based on supervised models.
Therefore, the automatic image analysis based on artificial neural networks is introduced to optimize it.
To address the above problems, we propose an end-to-end multi-category instance segmentation model, namely Semantic Attention and Scale Complementary Network, which mainly consists of a Semantic Attention (SEA) module and a Scale Complementary Mask Branch (SCMB).
In recent years, deep learning has made brilliant achievements in Environmental Microorganism (EM) image classification.
With the booming of online social networks in the mobile internet, an emerging recommendation scenario has played a vital role in information acquisition for user, where users are no longer recommended with a single item or item list, but a combination of heterogeneous and diverse objects (called a package, e. g., a package including news, publisher, and friends viewing the news).
Histological subtype of papillary (p) renal cell carcinoma (RCC), type 1 vs. type 2, is an essential prognostic factor.
It is desirable to transfer the knowledge stored in a well-trained source model onto non-annotated target domain in the absence of source data.
We conclude that ViT performs the worst in classifying 8 * 8 pixel patches, but it outperforms most convolutional neural networks in classifying 224 * 224 pixel patches.
In this paper, we propose a Composite High-Resolution Network for ccRCC nuclei grading.
Interpreting how does deep neural networks (DNNs) make predictions is a vital field in artificial intelligence, which hinders wide applications of DNNs.
In order to prove that the methods of different periods in the field of image classification have discrepancies on GasHisSDB, we select a variety of classifiers for evaluation.
In this paper, we first briefly review the development of Convolutional Neural Network and Visual Transformer in deep learning, and introduce the sources and development of conventional noises and adversarial attacks.
The results of the study indicate that deep learning models are robust to changes in the aspect ratio of cells in cervical cytopathological images.
In this review, first, we analyse the existing microorganism detection methods in chronological order, from traditional image processing and traditional machine learning to deep learning methods.
In this paper, a multi-scale visual transformer model, referred as GasHis-Transformer, is proposed for Gastric Histopathological Image Detection (GHID), which enables the automatic global detection of gastric cancer images.
1 code implementation • 26 Apr 2021 • Wei Zeng, Xiaozhe Ren, Teng Su, Hui Wang, Yi Liao, Zhiwei Wang, Xin Jiang, ZhenZhang Yang, Kaisheng Wang, Xiaoda Zhang, Chen Li, Ziyan Gong, Yifan Yao, Xinjing Huang, Jun Wang, Jianfeng Yu, Qi Guo, Yue Yu, Yan Zhang, Jin Wang, Hengtao Tao, Dasen Yan, Zexuan Yi, Fang Peng, Fangqing Jiang, Han Zhang, Lingfeng Deng, Yehong Zhang, Zhe Lin, Chao Zhang, Shaojie Zhang, Mingyue Guo, Shanzhi Gu, Gaojun Fan, YaoWei Wang, Xuefeng Jin, Qun Liu, Yonghong Tian
To enhance the generalization ability of PanGu-$\alpha$, we collect 1. 1TB high-quality Chinese data from a wide range of domains to pretrain the model.
Ranked #1 on Reading Comprehension (Zero-Shot) on CMRC 2018
Finally, the application prospect of the analytical method in this field is discussed.
Existing works circumvent this problem with pseudo labels generated from data of other easily accessible domains such as synthetic data.
In this article, we have studied the development of microorganism counting methods using digital image analysis.
Decision of transfer layers and trainable layers is a major task for design of the transfer convolutional neural networks (CNN).
In order to fasten, low the cost, increase consistency and accuracy of identification, we propose the novel pairwise deep learning features to analyze microorganisms.
Pap smear test is a widely performed screening technique for early detection of cervical cancer, whereas this manual screening method suffers from high false-positive results because of human errors.
This paper reviews the methods of WSI analysis based on machine learning.
The HCRF-AM model consists of an Attention Mechanism (AM) module and an Image Classification (IC) module.
EMDS-5 can realize to evaluate image preprocessing, image segmentation, feature extraction, image classification and image retrieval functions.
In this paper, we propose Cocktail Edge Caching, that tackles the dynamic popularity and heterogeneity through ensemble learning.
The Propositional Satisfiability Problem (SAT), and more generally, the Constraint Satisfaction Problem (CSP), are mathematical questions defined as finding an assignment to a set of objects that satisfies a series of constraints.
To deeply study this task, we present SportsSum, a Chinese sports game summarization dataset which contains 5, 428 soccer games of live commentaries and the corresponding news articles.
Instead, we investigate several less-studied aspects of neural abstractive summarization, including (i) the importance of selecting important segments from transcripts to serve as input to the summarizer; (ii) striking a balance between the amount and quality of training instances; (iii) the appropriate summary length and start/end points.
This indicates that the double-peaked structure in the light curve of the bursts may be affected by enhanced accretion rate in the disc, or increased temperature of the neutron star.
High Energy Astrophysical Phenomena
Chinese spelling check is a challenging task due to the characteristics of the Chinese language, such as the large character set, no word boundary, and short word length.
In this review, we present a comprehensive overview of pathology image analysis based on the markov random fields (MRFs) and conditional random fields (CRFs), which are two popular random field models.
In this paper, we propose a weakly supervised deep generative network to address the inverse problem and circumvent the need for ground truth 2D-to-3D correspondences.
Semi-supervised learning (SSL) is an effective way to utilize unlabeled data and alleviate the need for labeled data.
Furthermore, the learned representations are disentangled with latent preference factors by a neighborhood routing algorithm, which can enhance expressiveness and interpretability.
In this paper, we achieve partially explainable learning model by symbolically explaining the role of activation functions (AF) under a scalable topology.
Recently, graph-based algorithms have drawn much attention because of their impressive success in semi-supervised setups.
In this model, we mapped the feature data to a quantum state in Hilbert space firstly, and then implement unitary evolution on it, in the end, we can get the classification result by im-plement measurement on the quantum state.
In this paper, We propose a general Riemannian proximal optimization algorithm with guaranteed convergence to solve Markov decision process (MDP) problems.
The technique of Cross-Lingual Word Embedding (CLWE) plays a fundamental role in tackling Natural Language Processing challenges for low-resource languages.
Breast cancer is one of the most common and deadliest cancers among women.
Behavior description is conducive to the analysis of tiny objects, similar objects, objects with weak visual information and objects with similar visual information, playing a fundamental role in the identification and classification of dynamic objects in microscopic videos.
In order to assist researchers to identify Environmental Microorganisms (EMs) effectively, a Multi-scale CNN-CRF (MSCC) framework for the EM image segmentation is proposed in this paper.
This HCRF model is built up with higher order potentials, including pixel-level and patch-level potentials, and graph-based post-processing is applied to further improve its segmentation performance.
Transition from conventional to digital pathology requires a new category of biomedical informatic infrastructure which could facilitate delicate pathological routine.
In classification, state-of-the-art deep learning-based classifiers perform better when trained by pixel-wise annotation dataset.
If generating a word can introduce an erroneous relation to the summary, the behavior must be discouraged.
Ranked #23 on Text Summarization on GigaWord
In this paper, we propose a hybrid text normalization system using multi-head self-attention.
Existing methods on news recommendation mainly include collaborative filtering methods which rely on direct user-item interactions and content based methods which characterize the content of user reading history.
Emerged as one of the best performing techniques for extractive summarization, determinantal point processes select the most probable set of sentences to form a summary according to a probability measure defined by modeling sentence prominence and pairwise repulsion.
Previous work on cross-lingual sequence labeling tasks either requires parallel data or bridges the two languages through word-byword matching.
Coreference resolution is an important task for gaining more complete understanding about texts by artificial intelligence.
Claims database and electronic health records database do not usually capture kinship or family relationship information, which is imperative for genetic research.
In the second stage, a viewport quality network (VQ-net) is designed to rate the VQA score for each proposed viewport, in which the saliency map of the viewport is predicted and then utilized in VQA score rating.
We argue that 3D human pose estimation from a monocular input is an inverse problem where multiple feasible solutions can exist.
Words are annotated in fine-grained and coarse-grained labels.
Ranked #14 on Sentiment Analysis on SST-5 Fine-grained classification
By treating relations and multi-hop paths as two different input sources, we use a feature extractor, which is shared by two downstream components (i. e. relation classifier and source discriminator), to capture shared/similar information between them.
Deep neural networks (DNNs) have shown huge superiority over humans in image recognition, speech processing, autonomous vehicles and medical diagnosis.
To fill in the gap between subjective quality and human behavior, this paper proposes a large-scale visual quality assessment (VQA) dataset of omnidirectional video, called VQA-OV, which collects 60 reference sequences and 540 impaired sequences.
In the correction stage, candidates were generated by the three GEC models and then merged to output the final corrections for M and S types.
This paper describes our submissions for SemEval-2018 Task 8: Semantic Extraction from CybersecUrity REports using NLP.
We investigate a series of learning kernel problems with polynomial combinations of base kernels, which will help us solve regression and classification problems.
In this paper, we present RKD-SLAM, a robust keyframe-based dense SLAM approach for an RGB-D camera that can robustly handle fast motion and dense loop closure, and run without time limitation in a moderate size scene.
For argumentation mining, there are several sub-tasks such as argumentation component type classification, relation classification.