Paper Group ANR 115
The Language of Legal and Illegal Activity on the Darknet. Should we Embed? A Study on the Online Performance of Utilizing Embeddings for Real-Time Job Recommendations. HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization. Reference-less Quality Estimation of Text Simplification Systems. Vietname …
The Language of Legal and Illegal Activity on the Darknet
| Title | The Language of Legal and Illegal Activity on the Darknet |
| Authors | Leshem Choshen, Dan Eldad, Daniel Hershcovich, Elior Sulem, Omri Abend |
| Abstract | The non-indexed parts of the Internet (the Darknet) have become a haven for both legal and illegal anonymous activity. Given the magnitude of these networks, scalably monitoring their activity necessarily relies on automated tools, and notably on NLP tools. However, little is known about what characteristics texts communicated through the Darknet have, and how well off-the-shelf NLP tools do on this domain. This paper tackles this gap and performs an in-depth investigation of the characteristics of legal and illegal text in the Darknet, comparing it to a clear net website with similar content as a control condition. Taking drug-related websites as a test case, we find that texts for selling legal and illegal drugs have several linguistic characteristics that distinguish them from one another, as well as from the control condition, among them the distribution of POS tags, and the coverage of their named entities in Wikipedia. |
| Tasks | |
| Published | 2019-05-14 |
| URL | https://arxiv.org/abs/1905.05543v2 |
| https://arxiv.org/pdf/1905.05543v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-language-of-legal-and-illegal-activity-on |
| Repo | |
| Framework | |
Should we Embed? A Study on the Online Performance of Utilizing Embeddings for Real-Time Job Recommendations
| Title | Should we Embed? A Study on the Online Performance of Utilizing Embeddings for Real-Time Job Recommendations |
| Authors | Markus Reiter-Haas, Emanuel Lacic, Tomislav Duricic, Valentin Slawicek, Elisabeth Lex |
| Abstract | In this work, we present the findings of an online study, where we explore the impact of utilizing embeddings to recommend job postings under real-time constraints. On the Austrian job platform Studo Jobs, we evaluate two popular recommendation scenarios: (i) providing similar jobs and, (ii) personalizing the job postings that are shown on the homepage. Our results show that for recommending similar jobs, we achieve the best online performance in terms of Click-Through Rate when we employ embeddings based on the most recent interaction. To personalize the job postings shown on a user’s homepage, however, combining embeddings based on the frequency and recency with which a user interacts with job postings results in the best online performance. |
| Tasks | |
| Published | 2019-07-15 |
| URL | https://arxiv.org/abs/1907.06556v1 |
| https://arxiv.org/pdf/1907.06556v1.pdf | |
| PWC | https://paperswithcode.com/paper/should-we-embed-a-study-on-the-online |
| Repo | |
| Framework | |
HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization
| Title | HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization |
| Authors | Xingxing Zhang, Furu Wei, Ming Zhou |
| Abstract | Neural extractive summarization models usually employ a hierarchical encoder for document encoding and they are trained using sentence-level labels, which are created heuristically using rule-based methods. Training the hierarchical encoder with these \emph{inaccurate} labels is challenging. Inspired by the recent work on pre-training transformer sentence encoders \cite{devlin:2018:arxiv}, we propose {\sc Hibert} (as shorthand for {\bf HI}erachical {\bf B}idirectional {\bf E}ncoder {\bf R}epresentations from {\bf T}ransformers) for document encoding and a method to pre-train it using unlabeled data. We apply the pre-trained {\sc Hibert} to our summarization model and it outperforms its randomly initialized counterpart by 1.25 ROUGE on the CNN/Dailymail dataset and by 2.0 ROUGE on a version of New York Times dataset. We also achieve the state-of-the-art performance on these two datasets. |
| Tasks | Document Summarization |
| Published | 2019-05-16 |
| URL | https://arxiv.org/abs/1905.06566v1 |
| https://arxiv.org/pdf/1905.06566v1.pdf | |
| PWC | https://paperswithcode.com/paper/hibert-document-level-pre-training-of |
| Repo | |
| Framework | |
Reference-less Quality Estimation of Text Simplification Systems
| Title | Reference-less Quality Estimation of Text Simplification Systems |
| Authors | Louis Martin, Samuel Humeau, Pierre-Emmanuel Mazaré, Antoine Bordes, Éric Villemonte de La Clergerie, Benoît Sagot |
| Abstract | The evaluation of text simplification (TS) systems remains an open challenge. As the task has common points with machine translation (MT), TS is often evaluated using MT metrics such as BLEU. However, such metrics require high quality reference data, which is rarely available for TS. TS has the advantage over MT of being a monolingual task, which allows for direct comparisons to be made between the simplified text and its original version. In this paper, we compare multiple approaches to reference-less quality estimation of sentence-level text simplification systems, based on the dataset used for the QATS 2016 shared task. We distinguish three different dimensions: gram-maticality, meaning preservation and simplicity. We show that n-gram-based MT metrics such as BLEU and METEOR correlate the most with human judgment of grammaticality and meaning preservation, whereas simplicity is best evaluated by basic length-based metrics. |
| Tasks | Machine Translation, Text Simplification |
| Published | 2019-01-30 |
| URL | http://arxiv.org/abs/1901.10746v1 |
| http://arxiv.org/pdf/1901.10746v1.pdf | |
| PWC | https://paperswithcode.com/paper/reference-less-quality-estimation-of-text |
| Repo | |
| Framework | |
Vietnamese transition-based dependency parsing with supertag features
| Title | Vietnamese transition-based dependency parsing with supertag features |
| Authors | Kiet Van Nguyen, Ngan Luu-Thuy Nguyen |
| Abstract | In recent years, dependency parsing is a fascinating research topic and has a lot of applications in natural language processing. In this paper, we present an effective approach to improve dependency parsing by utilizing supertag features. We performed experiments with the transition-based dependency parsing approach because it can take advantage of rich features. Empirical evaluation on Vietnamese Dependency Treebank showed that, we achieved an improvement of 18.92% in labeled attachment score with gold supertags and an improvement of 3.57% with automatic supertags. |
| Tasks | Dependency Parsing, Transition-Based Dependency Parsing |
| Published | 2019-11-09 |
| URL | https://arxiv.org/abs/1911.03726v1 |
| https://arxiv.org/pdf/1911.03726v1.pdf | |
| PWC | https://paperswithcode.com/paper/vietnamese-transition-based-dependency |
| Repo | |
| Framework | |
Learning a Layout Transfer Network for Context Aware Object Detection
| Title | Learning a Layout Transfer Network for Context Aware Object Detection |
| Authors | Tao Wang, Xuming He, Yuanzheng Cai, Guobao Xiao |
| Abstract | We present a context aware object detection method based on a retrieve-and-transform scene layout model. Given an input image, our approach first retrieves a coarse scene layout from a codebook of typical layout templates. In order to handle large layout variations, we use a variant of the spatial transformer network to transform and refine the retrieved layout, resulting in a set of interpretable and semantically meaningful feature maps of object locations and scales. The above steps are implemented as a Layout Transfer Network which we integrate into Faster RCNN to allow for joint reasoning of object detection and scene layout estimation. Extensive experiments on three public datasets verified that our approach provides consistent performance improvements to the state-of-the-art object detection baselines on a variety of challenging tasks in the traffic surveillance and the autonomous driving domains. |
| Tasks | Autonomous Driving, Object Detection |
| Published | 2019-12-09 |
| URL | https://arxiv.org/abs/1912.03865v1 |
| https://arxiv.org/pdf/1912.03865v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-a-layout-transfer-network-for |
| Repo | |
| Framework | |
Domain invariant hierarchical embedding for grocery products recognition
| Title | Domain invariant hierarchical embedding for grocery products recognition |
| Authors | Alessio Tonioni, Luigi Di Stefano |
| Abstract | Recognizing packaged grocery products based solely on appearance is still an open issue for modern computer vision systems due to peculiar challenges. Firstly, the number of different items to be recognized is huge (i.e., in the order of thousands) and rapidly changing over time. Moreover, there exist a significant domain shift between the images that should be recognized at test time, taken in stores by cheap cameras, and those available for training, usually just one or a few studio-quality images per product. We propose an end-to-end architecture comprising a GAN to address the domain shift at training time and a deep CNN trained on the samples generated by the GAN to learn an embedding of product images that enforces a hierarchy between product categories. At test time, we perform recognition by means of K-NN search against a database consisting of just one reference image per product. Experiments addressing recognition of products present in the training datasets as well as different ones unseen at training time show that our approach compares favourably to state-of-the-art methods on the grocery recognition task and generalize fairly well to similar ones. |
| Tasks | |
| Published | 2019-02-02 |
| URL | http://arxiv.org/abs/1902.00760v1 |
| http://arxiv.org/pdf/1902.00760v1.pdf | |
| PWC | https://paperswithcode.com/paper/domain-invariant-hierarchical-embedding-for |
| Repo | |
| Framework | |
EleAtt-RNN: Adding Attentiveness to Neurons in Recurrent Neural Networks
| Title | EleAtt-RNN: Adding Attentiveness to Neurons in Recurrent Neural Networks |
| Authors | Pengfei Zhang, Jianru Xue, Cuiling Lan, Wenjun Zeng, Zhanning Gao, Nanning Zheng |
| Abstract | Recurrent neural networks (RNNs) are capable of modeling temporal dependencies of complex sequential data. In general, current available structures of RNNs tend to concentrate on controlling the contributions of current and previous information. However, the exploration of different importance levels of different elements within an input vector is always ignored. We propose a simple yet effective Element-wise-Attention Gate (EleAttG), which can be easily added to an RNN block (e.g. all RNN neurons in an RNN layer), to empower the RNN neurons to have attentiveness capability. For an RNN block, an EleAttG is used for adaptively modulating the input by assigning different levels of importance, i.e., attention, to each element/dimension of the input. We refer to an RNN block equipped with an EleAttG as an EleAtt-RNN block. Instead of modulating the input as a whole, the EleAttG modulates the input at fine granularity, i.e., element-wise, and the modulation is content adaptive. The proposed EleAttG, as an additional fundamental unit, is general and can be applied to any RNN structures, e.g., standard RNN, Long Short-Term Memory (LSTM), or Gated Recurrent Unit (GRU). We demonstrate the effectiveness of the proposed EleAtt-RNN by applying it to different tasks including the action recognition, from both skeleton-based data and RGB videos, gesture recognition, and sequential MNIST classification. Experiments show that adding attentiveness through EleAttGs to RNN blocks significantly improves the power of RNNs. |
| Tasks | Gesture Recognition, Skeleton Based Action Recognition |
| Published | 2019-09-03 |
| URL | https://arxiv.org/abs/1909.01939v1 |
| https://arxiv.org/pdf/1909.01939v1.pdf | |
| PWC | https://paperswithcode.com/paper/eleatt-rnn-adding-attentiveness-to-neurons-in |
| Repo | |
| Framework | |
Social Relation Recognition in Egocentric Photostreams
| Title | Social Relation Recognition in Egocentric Photostreams |
| Authors | Emanuel Sanchez Aimar, Petia Radeva, Mariella Dimiccoli |
| Abstract | This paper proposes an approach to automatically categorize the social interactions of a user wearing a photo-camera 2fpm, by relying solely on what the camera is seeing. The problem is challenging due to the overwhelming complexity of social life and the extreme intra-class variability of social interactions captured under unconstrained conditions. We adopt the formalization proposed in Bugental’s social theory, that groups human relations into five social domains with related categories. Our method is a new deep learning architecture that exploits the hierarchical structure of the label space and relies on a set of social attributes estimated at frame level to provide a semantic representation of social interactions. Experimental results on the new EgoSocialRelation dataset demonstrate the effectiveness of our proposal. |
| Tasks | |
| Published | 2019-05-12 |
| URL | https://arxiv.org/abs/1905.04734v1 |
| https://arxiv.org/pdf/1905.04734v1.pdf | |
| PWC | https://paperswithcode.com/paper/social-relation-recognition-in-egocentric |
| Repo | |
| Framework | |
A large annotated medical image dataset for the development and evaluation of segmentation algorithms
| Title | A large annotated medical image dataset for the development and evaluation of segmentation algorithms |
| Authors | Amber L. Simpson, Michela Antonelli, Spyridon Bakas, Michel Bilello, Keyvan Farahani, Bram van Ginneken, Annette Kopp-Schneider, Bennett A. Landman, Geert Litjens, Bjoern Menze, Olaf Ronneberger, Ronald M. Summers, Patrick Bilic, Patrick F. Christ, Richard K. G. Do, Marc Gollub, Jennifer Golia-Pernicka, Stephan H. Heckers, William R. Jarnagin, Maureen K. McHugo, Sandy Napel, Eugene Vorontsov, Lena Maier-Hein, M. Jorge Cardoso |
| Abstract | Semantic segmentation of medical images aims to associate a pixel with a label in a medical image without human initialization. The success of semantic segmentation algorithms is contingent on the availability of high-quality imaging data with corresponding labels provided by experts. We sought to create a large collection of annotated medical image datasets of various clinically relevant anatomies available under open source license to facilitate the development of semantic segmentation algorithms. Such a resource would allow: 1) objective assessment of general-purpose segmentation methods through comprehensive benchmarking and 2) open and free access to medical image data for any researcher interested in the problem domain. Through a multi-institutional effort, we generated a large, curated dataset representative of several highly variable segmentation tasks that was used in a crowd-sourced challenge - the Medical Segmentation Decathlon held during the 2018 Medical Image Computing and Computer Aided Interventions Conference in Granada, Spain. Here, we describe these ten labeled image datasets so that these data may be effectively reused by the research community. |
| Tasks | Semantic Segmentation |
| Published | 2019-02-25 |
| URL | http://arxiv.org/abs/1902.09063v1 |
| http://arxiv.org/pdf/1902.09063v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-large-annotated-medical-image-dataset-for |
| Repo | |
| Framework | |
Doppler Invariant Demodulation for Shallow Water Acoustic Communications Using Deep Belief Networks
| Title | Doppler Invariant Demodulation for Shallow Water Acoustic Communications Using Deep Belief Networks |
| Authors | Abigail Lee-Leon, Chau Yuen, Dorien Herremans |
| Abstract | Shallow water environments create a challenging channel for communications. In this paper, we focus on the challenges posed by the frequency-selective signal distortion called the Doppler effect. We explore the design and performance of machine learning (ML) based demodulation methods — (1) Deep Belief Network-feed forward Neural Network (DBN-NN) and (2) Deep Belief Network-Convolutional Neural Network (DBN-CNN) in the physical layer of Shallow Water Acoustic Communication (SWAC). The proposed method comprises of a ML based feature extraction method and classification technique. First, the feature extraction converts the received signals to feature images. Next, the classification model correlates the images to a corresponding binary representative. An analysis of the ML based proposed demodulation shows that despite the presence of instantaneous frequencies, the performance of the algorithm shows an invariance with a small 2dB error margin in terms of bit error rate (BER). |
| Tasks | |
| Published | 2019-09-05 |
| URL | https://arxiv.org/abs/1909.02850v1 |
| https://arxiv.org/pdf/1909.02850v1.pdf | |
| PWC | https://paperswithcode.com/paper/doppler-invariant-demodulation-for-shallow |
| Repo | |
| Framework | |
From Pixels to Affect: A Study on Games and Player Experience
| Title | From Pixels to Affect: A Study on Games and Player Experience |
| Authors | Konstantinos Makantasis, Antonios Liapis, Georgios N. Yannakakis |
| Abstract | Is it possible to predict the affect of a user just by observing her behavioral interaction through a video? How can we, for instance, predict a user’s arousal in games by merely looking at the screen during play? In this paper we address these questions by employing three dissimilar deep convolutional neural network architectures in our attempt to learn the underlying mapping between video streams of gameplay and the player’s arousal. We test the algorithms in an annotated dataset of 50 gameplay videos of a survival shooter game and evaluate the deep learned models’ capacity to classify high vs low arousal levels. Our key findings with the demanding leave-one-video-out validation method reveal accuracies of over 78% on average and 98% at best. While this study focuses on games and player experience as a test domain, the findings and methodology are directly relevant to any affective computing area, introducing a general and user-agnostic approach for modeling affect. |
| Tasks | |
| Published | 2019-07-04 |
| URL | https://arxiv.org/abs/1907.02288v2 |
| https://arxiv.org/pdf/1907.02288v2.pdf | |
| PWC | https://paperswithcode.com/paper/from-pixels-to-affect-a-study-on-games-and |
| Repo | |
| Framework | |
Volumetric Convolution: Automatic Representation Learning in Unit Ball
| Title | Volumetric Convolution: Automatic Representation Learning in Unit Ball |
| Authors | Sameera Ramasinghe, Salman Khan, Nick Barnes |
| Abstract | Convolution is an efficient technique to obtain abstract feature representations using hierarchical layers in deep networks. Although performing convolution in Euclidean geometries is fairly straightforward, its extension to other topological spaces—such as a sphere ($\mathbb{S}^2$) or a unit ball ($\mathbb{B}^3$)—entails unique challenges. In this work, we propose a novel `\emph{volumetric convolution}’ operation that can effectively convolve arbitrary functions in $\mathbb{B}^3$. We develop a theoretical framework for \emph{volumetric convolution} based on Zernike polynomials and efficiently implement it as a differentiable and an easily pluggable layer for deep networks. Furthermore, our formulation leads to derivation of a novel formula to measure the symmetry of a function in $\mathbb{B}^3$ around an arbitrary axis, that is useful in 3D shape analysis tasks. We demonstrate the efficacy of proposed volumetric convolution operation on a possible use-case i.e., 3D object recognition task. | |
| Tasks | 3D Object Recognition, 3D Shape Analysis, Object Recognition, Representation Learning |
| Published | 2019-01-03 |
| URL | http://arxiv.org/abs/1901.00616v1 |
| http://arxiv.org/pdf/1901.00616v1.pdf | |
| PWC | https://paperswithcode.com/paper/volumetric-convolution-automatic |
| Repo | |
| Framework | |
GraSPy: Graph Statistics in Python
| Title | GraSPy: Graph Statistics in Python |
| Authors | Jaewon Chung, Benjamin D. Pedigo, Eric W. Bridgeford, Bijan K. Varjavand, Hayden S. Helm, Joshua T. Vogelstein |
| Abstract | We introduce GraSPy, a Python library devoted to statistical inference, machine learning, and visualization of random graphs and graph populations. This package provides flexible and easy-to-use algorithms for analyzing and understanding graphs with a scikit-learn compliant API. GraSPy can be downloaded from Python Package Index (PyPi), and is released under the Apache 2.0 open-source license. The documentation and all releases are available at https://neurodata.io/graspy. |
| Tasks | |
| Published | 2019-03-29 |
| URL | https://arxiv.org/abs/1904.05329v3 |
| https://arxiv.org/pdf/1904.05329v3.pdf | |
| PWC | https://paperswithcode.com/paper/graspy-graph-statistics-in-python |
| Repo | |
| Framework | |
Applying SVGD to Bayesian Neural Networks for Cyclical Time-Series Prediction and Inference
| Title | Applying SVGD to Bayesian Neural Networks for Cyclical Time-Series Prediction and Inference |
| Authors | Xinyu Hu, Paul Szerlip, Theofanis Karaletsos, Rohit Singh |
| Abstract | A regression-based BNN model is proposed to predict spatiotemporal quantities like hourly rider demand with calibrated uncertainties. The main contributions of this paper are (i) A feed-forward deterministic neural network (DetNN) architecture that predicts cyclical time series data with sensitivity to anomalous forecasting events; (ii) A Bayesian framework applying SVGD to train large neural networks for such tasks, capable of producing time series predictions as well as measures of uncertainty surrounding the predictions. Experiments show that the proposed BNN reduces average estimation error by 10% across 8 U.S. cities compared to a fine-tuned multilayer perceptron (MLP), and 4% better than the same network architecture trained without SVGD. |
| Tasks | Time Series, Time Series Prediction |
| Published | 2019-01-17 |
| URL | http://arxiv.org/abs/1901.05906v1 |
| http://arxiv.org/pdf/1901.05906v1.pdf | |
| PWC | https://paperswithcode.com/paper/applying-svgd-to-bayesian-neural-networks-for |
| Repo | |
| Framework | |
