Paper Group ANR 1495
Enriching Medcial Terminology Knowledge Bases via Pre-trained Language Model and Graph Convolutional Network. Ask less - Scale Market Research without Annoying Your Customers. BiRA-Net: Bilinear Attention Net for Diabetic Retinopathy Grading. Weighted graphlets and deep neural networks for protein structure classification. Bold Hearts Team Descript …
Enriching Medcial Terminology Knowledge Bases via Pre-trained Language Model and Graph Convolutional Network
| Title | Enriching Medcial Terminology Knowledge Bases via Pre-trained Language Model and Graph Convolutional Network |
| Authors | Jiaying Zhang, Zhixing Zhang, Huanhuan Zhang, Zhiyuan Ma, Yangming Zhou, Ping He |
| Abstract | Enriching existing medical terminology knowledge bases (KBs) is an important and never-ending work for clinical research because new terminology alias may be continually added and standard terminologies may be newly renamed. In this paper, we propose a novel automatic terminology enriching approach to supplement a set of terminologies to KBs. Specifically, terminology and entity characters are first fed into pre-trained language model to obtain semantic embedding. The pre-trained model is used again to initialize the terminology and entity representations, then they are further embedded through graph convolutional network to gain structure embedding. Afterwards, both semantic and structure embeddings are combined to measure the relevancy between the terminology and the entity. Finally, the optimal alignment is achieved based on the order of relevancy between the terminology and all the entities in the KB. Experimental results on clinical indicator terminology KB, collected from 38 top-class hospitals of Shanghai Hospital Development Center, show that our proposed approach outperforms baseline methods and can effectively enrich the KB. |
| Tasks | Language Modelling |
| Published | 2019-09-02 |
| URL | https://arxiv.org/abs/1909.00615v1 |
| https://arxiv.org/pdf/1909.00615v1.pdf | |
| PWC | https://paperswithcode.com/paper/enriching-medcial-terminology-knowledge-bases |
| Repo | |
| Framework | |
Ask less - Scale Market Research without Annoying Your Customers
| Title | Ask less - Scale Market Research without Annoying Your Customers |
| Authors | Venkatesh Umaashankar, Girish Shanmugam S |
| Abstract | Market research is generally performed by surveying a representative sample of customers with questions that includes contexts such as psycho-graphics, demographics, attitude and product preferences. Survey responses are used to segment the customers into various groups that are useful for targeted marketing and communication. Reducing the number of questions asked to the customer has utility for businesses to scale the market research to a large number of customers. In this work, we model this task using Bayesian networks. We demonstrate the effectiveness of our approach using an example market segmentation of broadband customers. |
| Tasks | |
| Published | 2019-01-25 |
| URL | http://arxiv.org/abs/1901.08744v1 |
| http://arxiv.org/pdf/1901.08744v1.pdf | |
| PWC | https://paperswithcode.com/paper/ask-less-scale-market-research-without |
| Repo | |
| Framework | |
BiRA-Net: Bilinear Attention Net for Diabetic Retinopathy Grading
| Title | BiRA-Net: Bilinear Attention Net for Diabetic Retinopathy Grading |
| Authors | Ziyuan Zhao, Kerui Zhang, Xuejie Hao, Jing Tian, Matthew Chin Heng Chua, Li Chen, Xin Xu |
| Abstract | Diabetic retinopathy (DR) is a common retinal disease that leads to blindness. For diagnosis purposes, DR image grading aims to provide automatic DR grade classification, which is not addressed in conventional research methods of binary DR image classification. Small objects in the eye images, like lesions and microaneurysms, are essential to DR grading in medical imaging, but they could easily be influenced by other objects. To address these challenges, we propose a new deep learning architecture, called BiRA-Net, which combines the attention model for feature extraction and bilinear model for fine-grained classification. Furthermore, in considering the distance between different grades of different DR categories, we propose a new loss function, called grading loss, which leads to improved training convergence of the proposed approach. Experimental results are provided to demonstrate the superior performance of the proposed approach. |
| Tasks | Image Classification |
| Published | 2019-05-15 |
| URL | https://arxiv.org/abs/1905.06312v2 |
| https://arxiv.org/pdf/1905.06312v2.pdf | |
| PWC | https://paperswithcode.com/paper/bira-net-bilinear-attention-net-for-diabetic |
| Repo | |
| Framework | |
Weighted graphlets and deep neural networks for protein structure classification
| Title | Weighted graphlets and deep neural networks for protein structure classification |
| Authors | Hongyu Guo, Khalique Newaz, Scott Emrich, Tijana Milenkovic, Jun Li |
| Abstract | As proteins with similar structures often have similar functions, analysis of protein structures can help predict protein functions and is thus important. We consider the problem of protein structure classification, which computationally classifies the structures of proteins into pre-defined groups. We develop a weighted network that depicts the protein structures, and more importantly, we propose the first graphlet-based measure that applies to weighted networks. Further, we develop a deep neural network (DNN) composed of both convolutional and recurrent layers to use this measure for classification. Put together, our approach shows dramatic improvements in performance over existing graphlet-based approaches on 36 real datasets. Even comparing with the state-of-the-art approach, it almost halves the classification error. In addition to protein structure networks, our weighted-graphlet measure and DNN classifier can potentially be applied to classification of other weighted networks in computational biology as well as in other domains. |
| Tasks | |
| Published | 2019-10-07 |
| URL | https://arxiv.org/abs/1910.02594v1 |
| https://arxiv.org/pdf/1910.02594v1.pdf | |
| PWC | https://paperswithcode.com/paper/weighted-graphlets-and-deep-neural-networks |
| Repo | |
| Framework | |
Bold Hearts Team Description for RoboCup 2019 (Humanoid Kid Size League)
| Title | Bold Hearts Team Description for RoboCup 2019 (Humanoid Kid Size League) |
| Authors | Marcus M. Scheunemann, Sander G. van Dijk, Rebecca Miko, Daniel Barry, George M. Evans, Alessandra Rossi, Daniel Polani |
| Abstract | We participated in the RoboCup 2018 competition in Montreal with our newly developed BoldBot based on the Darwin-OP and mostly self-printed custom parts. This paper is about the lessons learnt from that competition and further developments for the RoboCup 2019 competition. Firstly, we briefly introduce the team along with an overview of past achievements. We then present a simple, standalone 2D simulator we use for simplifying the entry for new members with making basic RoboCup concepts quickly accessible. We describe our approach for semantic-segmentation for our vision used in the 2018 competition, which replaced the lookup-table (LUT) implementation we had before. We also discuss the extra structural support we plan to add to the printed parts of the BoldBot and our transition to ROS 2 as our new middleware. Lastly, we will present a collection of open-source contributions of our team. |
| Tasks | Semantic Segmentation |
| Published | 2019-04-22 |
| URL | http://arxiv.org/abs/1904.10066v1 |
| http://arxiv.org/pdf/1904.10066v1.pdf | |
| PWC | https://paperswithcode.com/paper/bold-hearts-team-description-for-robocup-2019 |
| Repo | |
| Framework | |
Background Subtraction using Adaptive Singular Value Decomposition
| Title | Background Subtraction using Adaptive Singular Value Decomposition |
| Authors | Günther Reitberger, Tomas Sauer |
| Abstract | An important task when processing sensor data is to distinguish relevant from irrelevant data. This paper describes a method for an iterative singular value decomposition that maintains a model of the background via singular vectors spanning a subspace of the image space, thus providing a way to determine the amount of new information contained in an incoming frame. We update the singular vectors spanning the background space in a computationally efficient manner and provide the ability to perform block-wise updates, leading to a fast and robust adaptive SVD computation. The effects of those two properties and the success of the overall method to perform a state of the art background subtraction are shown in both qualitative and quantitative evaluations. |
| Tasks | |
| Published | 2019-06-28 |
| URL | https://arxiv.org/abs/1906.12064v1 |
| https://arxiv.org/pdf/1906.12064v1.pdf | |
| PWC | https://paperswithcode.com/paper/background-subtraction-using-adaptive |
| Repo | |
| Framework | |
Learning to Predict More Accurate Text Instances for Scene Text Detection
| Title | Learning to Predict More Accurate Text Instances for Scene Text Detection |
| Authors | XiaoQian Li, Jie Liu, ShuWu Zhang, GuiXuan Zhang |
| Abstract | At present, multi-oriented text detection methods based on deep neural network have achieved promising performances on various benchmarks. Nevertheless, there are still some difficulties for arbitrary shape text detection, especially for a simple and proper representation of arbitrary shape text instances. In this paper, a pixel-based text detector is proposed to facilitate the representation and prediction of text instances with arbitrary shapes in a simple manner. Firstly, to alleviate the effect of the target vertex sorting and achieve the direct regression of arbitrary shape text instances, the starting-point-independent coordinates regression loss is proposed. Furthermore, to predict more accurate text instances, the text instance accuracy loss is proposed as an assistant task to refine the predicted coordinates under the guidance of IoU. To evaluate the effectiveness of our detector, extensive experiments have been carried on public benchmarks. On the ICDAR 2015 Incidental Scene Text benchmark, our method achieves 86.5% of F-measure, and we obtain 84.8% of F-measure on Total-Text benchmark. The results show that our method can reach state-of-the-art performance. |
| Tasks | Scene Text Detection |
| Published | 2019-11-18 |
| URL | https://arxiv.org/abs/1911.07423v1 |
| https://arxiv.org/pdf/1911.07423v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-predict-more-accurate-text |
| Repo | |
| Framework | |
Computer Assisted Composition in Continuous Time
| Title | Computer Assisted Composition in Continuous Time |
| Authors | Chamin Hewa Koneputugodage, Rhys Healy, Sean Lamont, Ian Mallett, Matt Brown, Matt Walters, Ushini Attanayake, Libo Zhang, Roger T. Dean, Alexander Hunter, Charles Gretton, Christian Walder |
| Abstract | We address the problem of combining sequence models of symbolic music with user defined constraints. For typical models this is non-trivial as only the conditional distribution of each symbol given the earlier symbols is available, while the constraints correspond to arbitrary times. Previously this has been addressed by assuming a discrete time model of fixed rhythm. We generalise to continuous time and arbitrary rhythm by introducing a simple, novel, and efficient particle filter scheme, applicable to general continuous time point processes. Extensive experimental evaluations demonstrate that in comparison with a more traditional beam search baseline, the particle filter exhibits superior statistical properties and yields more agreeable results in an extensive human listening test experiment. |
| Tasks | Point Processes |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1909.05030v1 |
| https://arxiv.org/pdf/1909.05030v1.pdf | |
| PWC | https://paperswithcode.com/paper/computer-assisted-composition-in-continuous |
| Repo | |
| Framework | |
TitAnt: Online Real-time Transaction Fraud Detection in Ant Financial
| Title | TitAnt: Online Real-time Transaction Fraud Detection in Ant Financial |
| Authors | Shaosheng Cao, Xinxing Yang, Cen Chen, Jun Zhou, Xiaolong Li, Yuan Qi |
| Abstract | With the explosive growth of e-commerce and the booming of e-payment, detecting online transaction fraud in real time has become increasingly important to Fintech business. To tackle this problem, we introduce the TitAnt, a transaction fraud detection system deployed in Ant Financial, one of the largest Fintech companies in the world. The system is able to predict online real-time transaction fraud in mere milliseconds. We present the problem definition, feature extraction, detection methods, implementation and deployment of the system, as well as empirical effectiveness. Extensive experiments have been conducted on large real-world transaction data to show the effectiveness and the efficiency of the proposed system. |
| Tasks | Fraud Detection |
| Published | 2019-06-18 |
| URL | https://arxiv.org/abs/1906.07407v1 |
| https://arxiv.org/pdf/1906.07407v1.pdf | |
| PWC | https://paperswithcode.com/paper/titant-online-real-time-transaction-fraud |
| Repo | |
| Framework | |
Stochastic Gradient Methods with Block Diagonal Matrix Adaptation
| Title | Stochastic Gradient Methods with Block Diagonal Matrix Adaptation |
| Authors | Jihun Yun, Aurelie C. Lozano, Eunho Yang |
| Abstract | Adaptive gradient approaches that automatically adjust the learning rate on a per-feature basis have been very popular for training deep networks. This rich class of algorithms includes Adagrad, RMSprop, Adam, and recent extensions. All these algorithms have adopted diagonal matrix adaptation, due to the prohibitive computational burden of manipulating full matrices in high-dimensions. In this paper, we show that block-diagonal matrix adaptation can be a practical and powerful solution that can effectively utilize structural characteristics of deep learning architectures, and significantly improve convergence and out-of-sample generalization. We present a general framework with block-diagonal matrix updates via coordinate grouping, which includes counterparts of the aforementioned algorithms, prove their convergence in non-convex optimization, highlighting benefits compared to diagonal versions. In addition, we propose an efficient spectrum-clipping scheme that benefits from superior generalization performance of Sgd. Extensive experiments reveal that block-diagonal approaches achieve state-of-the-art results on several deep learning tasks, and can outperform adaptive diagonal methods, vanilla Sgd, as well as a modified version of full-matrix adaptation proposed very recently. |
| Tasks | |
| Published | 2019-05-26 |
| URL | https://arxiv.org/abs/1905.10757v1 |
| https://arxiv.org/pdf/1905.10757v1.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-gradient-methods-with-block |
| Repo | |
| Framework | |
Comparison of Classical Machine Learning Approaches on Bangla Textual Emotion Analysis
| Title | Comparison of Classical Machine Learning Approaches on Bangla Textual Emotion Analysis |
| Authors | Md. Ataur Rahman, Md. Hanif Seddiqui |
| Abstract | Detecting emotions from text is an extension of simple sentiment polarity detection. Instead of considering only positive or negative sentiments, emotions are conveyed using more tangible manner; thus, they can be expressed as many shades of gray. This paper manifests the results of our experimentation for fine-grained emotion analysis on Bangla text. We gathered and annotated a text corpus consisting of user comments from several Facebook groups regarding socio-economic and political issues, and we made efforts to extract the basic emotions (sadness, happiness, disgust, surprise, fear, anger) conveyed through these comments. Finally, we compared the results of the five most popular classical machine learning techniques namely Naive Bayes, Decision Tree, k-Nearest Neighbor (k-NN), Support Vector Machine (SVM) and K-Means Clustering with several combinations of features. Our best model (SVM with a non-linear radial-basis function (RBF) kernel) achieved an overall average accuracy score of 52.98% and an F1 score (macro) of 0.3324 |
| Tasks | Emotion Recognition |
| Published | 2019-07-18 |
| URL | https://arxiv.org/abs/1907.07826v1 |
| https://arxiv.org/pdf/1907.07826v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparison-of-classical-machine-learning |
| Repo | |
| Framework | |
Integrating Temporal Information to Spatial Information in a Neural Circuit
| Title | Integrating Temporal Information to Spatial Information in a Neural Circuit |
| Authors | Nancy Lynch, Mien Brabeeba Wang |
| Abstract | In this paper, we consider a network of spiking neurons with a deterministic synchronous firing rule at discrete time. We propose three problems – “first consecutive spikes counting”, “total spikes counting” and “$k$-spikes temporal to spatial encoding” – to model how brains extract temporal information into spatial information from different neural codings. For a max input length $T$, we design three networks that solve these three problems with matching lower bounds in both time $O(T)$ and number of neurons $O(\log T)$ in all three questions. |
| Tasks | |
| Published | 2019-03-01 |
| URL | https://arxiv.org/abs/1903.01217v2 |
| https://arxiv.org/pdf/1903.01217v2.pdf | |
| PWC | https://paperswithcode.com/paper/integrating-temporal-information-to-spatial |
| Repo | |
| Framework | |
Watch It Twice: Video Captioning with a Refocused Video Encoder
| Title | Watch It Twice: Video Captioning with a Refocused Video Encoder |
| Authors | Xiangxi Shi, Jianfei Cai, Shafiq Joty, Jiuxiang Gu |
| Abstract | With the rapid growth of video data and the increasing demands of various applications such as intelligent video search and assistance toward visually-impaired people, video captioning task has received a lot of attention recently in computer vision and natural language processing fields. The state-of-the-art video captioning methods focus more on encoding the temporal information, while lack of effective ways to remove irrelevant temporal information and also neglecting the spatial details. However, the current RNN encoding module in single time order can be influenced by the irrelevant temporal information, especially the irrelevant temporal information is at the beginning of the encoding. In addition, neglecting spatial information will lead to the relationship confusion of the words and detailed loss. Therefore, in this paper, we propose a novel recurrent video encoding method and a novel visual spatial feature for the video captioning task. The recurrent encoding module encodes the video twice with the predicted key frame to avoid the irrelevant temporal information often occurring at the beginning and the end of a video. The novel spatial features represent the spatial information in different regions of a video and enrich the details of a caption. Experiments on two benchmark datasets show superior performance of the proposed method. |
| Tasks | Video Captioning |
| Published | 2019-07-21 |
| URL | https://arxiv.org/abs/1907.12905v1 |
| https://arxiv.org/pdf/1907.12905v1.pdf | |
| PWC | https://paperswithcode.com/paper/watch-it-twice-video-captioning-with-a |
| Repo | |
| Framework | |
Identifying and Explaining Discriminative Attributes
| Title | Identifying and Explaining Discriminative Attributes |
| Authors | Armins Stepanjans, André Freitas |
| Abstract | Identifying what is at the center of the meaning of a word and what discriminates it from other words is a fundamental natural language inference task. This paper describes an explicit word vector representation model (WVM) to support the identification of discriminative attributes. A core contribution of the paper is a quantitative and qualitative comparative analysis of different types of data sources and Knowledge Bases in the construction of explainable and explicit WVMs: (i) knowledge graphs built from dictionary definitions, (ii) entity-attribute-relationships graphs derived from images and (iii) commonsense knowledge graphs. Using a detailed quantitative and qualitative analysis, we demonstrate that these data sources have complementary semantic aspects, supporting the creation of explicit semantic vector spaces. The explicit vector spaces are evaluated using the task of discriminative attribute identification, showing comparable performance to the state-of-the-art systems in the task (F1-score = 0.69), while delivering full model transparency and explainability. |
| Tasks | Knowledge Graphs, Natural Language Inference |
| Published | 2019-09-05 |
| URL | https://arxiv.org/abs/1909.05363v1 |
| https://arxiv.org/pdf/1909.05363v1.pdf | |
| PWC | https://paperswithcode.com/paper/identifying-and-explaining-discriminative |
| Repo | |
| Framework | |
Automatic Generation of Multi-precision Multi-arithmetic CNN Accelerators for FPGAs
| Title | Automatic Generation of Multi-precision Multi-arithmetic CNN Accelerators for FPGAs |
| Authors | Yiren Zhao, Xitong Gao, Xuan Guo, Junyi Liu, Erwei Wang, Robert Mullins, Peter Y. K. Cheung, George Constantinides, Cheng-Zhong Xu |
| Abstract | Modern deep Convolutional Neural Networks (CNNs) are computationally demanding, yet real applications often require high throughput and low latency. To help tackle these problems, we propose Tomato, a framework designed to automate the process of generating efficient CNN accelerators. The generated design is pipelined and each convolution layer uses different arithmetics at various precisions. Using Tomato, we showcase state-of-the-art multi-precision multi-arithmetic networks, including MobileNet-V1, running on FPGAs. To our knowledge, this is the first multi-precision multi-arithmetic auto-generation framework for CNNs. In software, Tomato fine-tunes pretrained networks to use a mixture of short powers-of-2 and fixed-point weights with a minimal loss in classification accuracy. The fine-tuned parameters are combined with the templated hardware designs to automatically produce efficient inference circuits in FPGAs. We demonstrate how our approach significantly reduces model sizes and computation complexities, and permits us to pack a complete ImageNet network onto a single FPGA without accessing off-chip memories for the first time. Furthermore, we show how Tomato produces implementations of networks with various sizes running on single or multiple FPGAs. To the best of our knowledge, our automatically generated accelerators outperform closest FPGA-based competitors by at least 2-4x for lantency and throughput; the generated accelerator runs ImageNet classification at a rate of more than 3000 frames per second. |
| Tasks | |
| Published | 2019-10-21 |
| URL | https://arxiv.org/abs/1910.10075v1 |
| https://arxiv.org/pdf/1910.10075v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-generation-of-multi-precision-multi |
| Repo | |
| Framework | |
