January 28, 2020

2919 words 14 mins read

Paper Group ANR 873

In Search of Meaning: Lessons, Resources and Next Steps for Computational Analysis of Financial Discourse. Toward Universal Testing of Dynamic Network Models. Maximizing Overall Diversity for Improved Uncertainty Estimates in Deep Ensembles. Semantic Search using Spreading Activation based on Ontology. RGPNet: A Real-Time General Purpose Semantic S …

In Search of Meaning: Lessons, Resources and Next Steps for Computational Analysis of Financial Discourse


Title	In Search of Meaning: Lessons, Resources and Next Steps for Computational Analysis of Financial Discourse
Authors	Mahmoud El-Haj, Paul Rayson, Martin Walker, Steven Young, Vasiliki Simaki
Abstract	We critically assess mainstream accounting and finance research applying methods from computational linguistics (CL) to study financial discourse. We also review common themes and innovations in the literature and assess the incremental contributions of work applying CL methods over manual content analysis. Key conclusions emerging from our analysis are: (a) accounting and finance research is behind the curve in terms of CL methods generally and word sense disambiguation in particular; (b) implementation issues mean the proposed benefits of CL are often less pronounced than proponents suggest; (c) structural issues limit practical relevance; and (d) CL methods and high quality manual analysis represent complementary approaches to analyzing financial discourse. We describe four CL tools that have yet to gain traction in mainstream AF research but which we believe offer promising ways to enhance the study of meaning in financial discourse. The four tools are named entity recognition (NER), summarization, semantics and corpus linguistics.
Tasks	Named Entity Recognition, Word Sense Disambiguation
Published	2019-03-28
URL	http://arxiv.org/abs/1903.12271v1
PDF	http://arxiv.org/pdf/1903.12271v1.pdf
PWC	https://paperswithcode.com/paper/in-search-of-meaning-lessons-resources-and
Repo
Framework

Toward Universal Testing of Dynamic Network Models


Title	Toward Universal Testing of Dynamic Network Models
Authors	Abram Magner, Wojciech Szpankowski
Abstract	Numerous networks in the real world change over time, in the sense that nodes and edges enter and leave the networks. Various dynamic random graph models have been proposed to explain the macroscopic properties of these systems and to provide a foundation for statistical inferences and predictions. It is of interest to have a rigorous way to determine how well these models match observed networks. We thus ask the following goodness of fit question: given a sequence of observations/snapshots of a growing random graph, along with a candidate model M, can we determine whether the snapshots came from M or from some arbitrary alternative model that is well-separated from M in some natural metric? We formulate this problem precisely and boil it down to goodness of fit testing for graph-valued, infinite-state Markov processes and exhibit and analyze a universal test based on non-stationary sampling for a natural class of models.
Tasks
Published	2019-04-06
URL	https://arxiv.org/abs/1904.03348v2
PDF	https://arxiv.org/pdf/1904.03348v2.pdf
PWC	https://paperswithcode.com/paper/goodness-of-fit-testing-for-dynamic-networks
Repo
Framework

Maximizing Overall Diversity for Improved Uncertainty Estimates in Deep Ensembles


Title	Maximizing Overall Diversity for Improved Uncertainty Estimates in Deep Ensembles
Authors	Siddhartha Jain, Ge Liu, Jonas Mueller, David Gifford
Abstract	The inaccuracy of neural network models on inputs that do not stem from the training data distribution is both problematic and at times unrecognized. Model uncertainty estimation can address this issue, where uncertainty estimates are often based on the variation in predictions produced by a diverse ensemble of models applied to the same input. Here we describe Maximize Overall Diversity (MOD), a straightforward approach to improve ensemble-based uncertainty estimates by encouraging larger overall diversity in ensemble predictions across all possible inputs that might be encountered in the future. When applied to various neural network ensembles, MOD significantly improves predictive performance for out-of-distribution test examples without sacrificing in-distribution performance on 38 Protein-DNA binding regression datasets, 9 UCI datasets, and the IMDB-Wiki image dataset. Across many Bayesian optimization tasks, the performance of UCB acquisition is also greatly improved by leveraging MOD uncertainty estimates.
Tasks
Published	2019-06-18
URL	https://arxiv.org/abs/1906.07380v2
PDF	https://arxiv.org/pdf/1906.07380v2.pdf
PWC	https://paperswithcode.com/paper/maximizing-overall-diversity-for-improved
Repo
Framework

Semantic Search using Spreading Activation based on Ontology


Title	Semantic Search using Spreading Activation based on Ontology
Authors	Ngo Minh Vuong
Abstract	Currently, the text document retrieval systems have many challenges in exploring the semantics of queries and documents. Each query implies information which does not appear in the query but the documents related with the information are also expected by user. The disadvantage of the previous spreading activation algorithms could be many irrelevant concepts added to the query. In this paper, a proposed novel algorithm is only activate and add to the query named entities which are related with original entities in the query and explicit relations in the query.
Tasks
Published	2019-05-09
URL	https://arxiv.org/abs/1905.06114v1
PDF	https://arxiv.org/pdf/1905.06114v1.pdf
PWC	https://paperswithcode.com/paper/190506114
Repo
Framework

RGPNet: A Real-Time General Purpose Semantic Segmentation


Title	RGPNet: A Real-Time General Purpose Semantic Segmentation
Authors	Elahe Arani, Shabbir Marzban, Andrei Pata, Bahram Zonooz
Abstract	We propose a novel real-time general purpose semantic segmentation architecture, called RGPNet, which achieves significant performance gain in complex environments. RGPNet consists of a light-weight asymmetric encoder-decoder and an adaptor. The adaptor helps preserve and refine the abstract concepts from multiple levels of distributed representations between encoder and decoder. It also facilitates the gradient flow from deeper layers to shallower layers. Our extensive experiments highlight the superior performance of RGPNet compared to the state-of-the-art semantic segmentation networks. Moreover, towards green AI, we show that using a modified label-relaxation technique with progressive resizing can reduce the training time by up to 60% while preserving the performance. Furthermore, we optimize RGPNet for resource-constrained and embedded devices which increases the inference speed by 400% with a negligible loss in performance. We conclude that RGPNet obtains a better speed-accuracy trade-off across multiple datasets.
Tasks	Semantic Segmentation
Published	2019-12-03
URL	https://arxiv.org/abs/1912.01394v1
PDF	https://arxiv.org/pdf/1912.01394v1.pdf
PWC	https://paperswithcode.com/paper/rgpnet-a-real-time-general-purpose-semantic
Repo
Framework

Deep MRI Reconstruction: Unrolled Optimization Algorithms Meet Neural Networks


Title	Deep MRI Reconstruction: Unrolled Optimization Algorithms Meet Neural Networks
Authors	Dong Liang, Jing Cheng, Ziwen Ke, Leslie Ying
Abstract	Image reconstruction from undersampled k-space data has been playing an important role for fast MRI. Recently, deep learning has demonstrated tremendous success in various fields and also shown potential to significantly speed up MR reconstruction with reduced measurements. This article gives an overview of deep learning-based image reconstruction methods for MRI. Three types of deep learning-based approaches are reviewed, the data-driven, model-driven and integrated approaches. The main structure of each network in three approaches is explained and the analysis of common parts of reviewed networks and differences in-between are highlighted. Based on the review, a number of signal processing issues are discussed for maximizing the potential of deep reconstruction for fast MRI. the discussion may facilitate further development of “optimal” network and performance analysis from a theoretical point of view.
Tasks	Image Reconstruction
Published	2019-07-26
URL	https://arxiv.org/abs/1907.11711v1
PDF	https://arxiv.org/pdf/1907.11711v1.pdf
PWC	https://paperswithcode.com/paper/deep-mri-reconstruction-unrolled-optimization
Repo
Framework

Improving Video Compression With Deep Visual-Attention Models


Title	Improving Video Compression With Deep Visual-Attention Models
Authors	Vitaliy Lyudvichenko, Mikhail Erofeev, Alexander Ploshkin, Dmitriy Vatolin
Abstract	Recent advances in deep learning have markedly improved the quality of visual-attention modelling. In this work we apply these advances to video compression. We propose a compression method that uses a saliency model to adaptively compress frame areas in accordance with their predicted saliency. We selected three state-of-the-art saliency models, adapted them for video compression and analyzed their results. The analysis includes objective evaluation of the models as well as objective and subjective evaluation of the compressed videos. Our method, which is based on the x264 video codec, can produce videos with the same visual quality as regular x264, but it reduces the bitrate by 25% according to the objective evaluation and by 17% according to the subjective one. Also, both the subjective and objective evaluations demonstrate that saliency models can compete with gaze maps for a single observer. Our method can extend to most video bitstream formats and can improve video compression quality without requiring a switch to a new video encoding standard.
Tasks	Video Compression
Published	2019-03-19
URL	http://arxiv.org/abs/1903.07912v1
PDF	http://arxiv.org/pdf/1903.07912v1.pdf
PWC	https://paperswithcode.com/paper/improving-video-compression-with-deep-visual
Repo
Framework

A Computationally Efficient Pipeline Approach to Full Page Offline Handwritten Text Recognition


Title	A Computationally Efficient Pipeline Approach to Full Page Offline Handwritten Text Recognition
Authors	Jonathan Chung, Thomas Delteil
Abstract	Offline handwriting recognition with deep neural networks is usually limited to words or lines due to large computational costs. In this paper, a less computationally expensive full page offline handwritten text recognition framework is introduced. This framework includes a pipeline that locates handwritten text with an object detection neural network and recognises the text within the detected regions using features extracted with a multi-scale convolutional neural network (CNN) fed into a bidirectional long short term memory (LSTM) network. This framework achieves comparable error rates to state of the art frameworks while using less memory and time. The results in this paper demonstrate the potential of this framework and future work can investigate production ready and deployable handwritten text recognisers.
Tasks	Object Detection
Published	2019-10-01
URL	https://arxiv.org/abs/1910.00663v1
PDF	https://arxiv.org/pdf/1910.00663v1.pdf
PWC	https://paperswithcode.com/paper/a-computationally-efficient-pipeline-approach
Repo
Framework

The SIGMORPHON 2019 Shared Task: Morphological Analysis in Context and Cross-Lingual Transfer for Inflection


Title	The SIGMORPHON 2019 Shared Task: Morphological Analysis in Context and Cross-Lingual Transfer for Inflection
Authors	Arya D. McCarthy, Ekaterina Vylomova, Shijie Wu, Chaitanya Malaviya, Lawrence Wolf-Sonkin, Garrett Nicolai, Christo Kirov, Miikka Silfverberg, Sabrina J. Mielke, Jeffrey Heinz, Ryan Cotterell, Mans Hulden
Abstract	The SIGMORPHON 2019 shared task on cross-lingual transfer and contextual analysis in morphology examined transfer learning of inflection between 100 language pairs, as well as contextual lemmatization and morphosyntactic description in 66 languages. The first task evolves past years’ inflection tasks by examining transfer of morphological inflection knowledge from a high-resource language to a low-resource language. This year also presents a new second challenge on lemmatization and morphological feature analysis in context. All submissions featured a neural component and built on either this year’s strong baselines or highly ranked systems from previous years’ shared tasks. Every participating team improved in accuracy over the baselines for the inflection task (though not Levenshtein distance), and every team in the contextual analysis task improved on both state-of-the-art neural and non-neural baselines.
Tasks	Cross-Lingual Transfer, Lemmatization, Morphological Analysis, Morphological Inflection, Transfer Learning
Published	2019-10-25
URL	https://arxiv.org/abs/1910.11493v2
PDF	https://arxiv.org/pdf/1910.11493v2.pdf
PWC	https://paperswithcode.com/paper/the-sigmorphon-2019-shared-task-morphological-1
Repo
Framework

Fast Projective Image Rectification for Planar Objects with Manhattan Structure


Title	Fast Projective Image Rectification for Planar Objects with Manhattan Structure
Authors	Julia Shemiakina, Ivan Konovalenko, Daniil Tropin, Igor Faradjev
Abstract	This paper presents a method for metric rectification of planar objects that preserves angles and length ratios. An inner structure of an object is assumed to follow the laws of Manhattan World i.e. the majority of line segments are aligned with two orthogonal directions of the object. For that purpose we introduce the method that estimates the position of two vanishing points corresponding to the main object directions. It is based on an original optimization function of segments that estimates a vanishing point position. For calculation of the rectification homography with two vanishing points we propose a new method based on estimation of the camera rotation so that the camera axis is perpendicular to the object plane. The proposed method can be applied for rectification of various objects such as documents or building facades. Also since the camera rotation is estimated the method can be employed for estimation of object orientation (for example, during a surgery with radiograph of osteosynthesis implants). The method was evaluated on the MIDV-500 dataset containing projectively distorted images of documents with complex background. According to the experimental results an accuracy of the proposed method is better or equal to the-state-of-the-art if the background occupies no more than half of the image. Runtime of the method is around 3ms on core i7 3610qm CPU.
Tasks
Published	2019-12-04
URL	https://arxiv.org/abs/1912.01892v1
PDF	https://arxiv.org/pdf/1912.01892v1.pdf
PWC	https://paperswithcode.com/paper/fast-projective-image-rectification-for
Repo
Framework

Intrusion Detection using Sequential Hybrid Model


Title	Intrusion Detection using Sequential Hybrid Model
Authors	Aditya Pandey, Abhishek Sinha, Aishwarya PS
Abstract	A large amount of work has been done on the KDD 99 dataset, most of which includes the use of a hybrid anomaly and misuse detection model done in parallel with each other. In order to further classify the intrusions, our approach to network intrusion detection includes use of two different anomaly detection models followed by misuse detection applied on the combined output obtained from the previous step. The end goal of this is to verify the anomalies detected by the anomaly detection algorithm and clarify whether they are actually intrusions or random outliers from the trained normal (and thus to try and reduce the number of false positives). We aim to detect a pattern in this novel intrusion technique itself, and not the handling of such intrusions. The intrusions were detected to a very high degree of accuracy.
Tasks	Anomaly Detection, Intrusion Detection, Network Intrusion Detection
Published	2019-10-26
URL	https://arxiv.org/abs/1910.12074v2
PDF	https://arxiv.org/pdf/1910.12074v2.pdf
PWC	https://paperswithcode.com/paper/intrusion-detection-using-sequential-hybrid
Repo
Framework

Pushing the Limits of Low-Resource Morphological Inflection


Title	Pushing the Limits of Low-Resource Morphological Inflection
Authors	Antonios Anastasopoulos, Graham Neubig
Abstract	Recent years have seen exceptional strides in the task of automatic morphological inflection generation. However, for a long tail of languages the necessary resources are hard to come by, and state-of-the-art neural methods that work well under higher resource settings perform poorly in the face of a paucity of data. In response, we propose a battery of improvements that greatly improve performance under such low-resource conditions. First, we present a novel two-step attention architecture for the inflection decoder. In addition, we investigate the effects of cross-lingual transfer from single and multiple languages, as well as monolingual data hallucination. The macro-averaged accuracy of our models outperforms the state-of-the-art by 15 percentage points. Also, we identify the crucial factors for success with cross-lingual transfer for morphological inflection: typological similarity and a common representation across languages.
Tasks	Cross-Lingual Transfer, Morphological Inflection
Published	2019-08-16
URL	https://arxiv.org/abs/1908.05838v2
PDF	https://arxiv.org/pdf/1908.05838v2.pdf
PWC	https://paperswithcode.com/paper/pushing-the-limits-of-low-resource
Repo
Framework

Deconstructing and reconstructing word embedding algorithms


Title	Deconstructing and reconstructing word embedding algorithms
Authors	Edward Newell, Kian Kenyon-Dean, Jackie Chi Kit Cheung
Abstract	Uncontextualized word embeddings are reliable feature representations of words used to obtain high quality results for various NLP applications. Given the historical success of word embeddings in NLP, we propose a retrospective on some of the most well-known word embedding algorithms. In this work, we deconstruct Word2vec, GloVe, and others, into a common form, unveiling some of the necessary and sufficient conditions required for making performant word embeddings. We find that each algorithm: (1) fits vector-covector dot products to approximate pointwise mutual information (PMI); and, (2) modulates the loss gradient to balance weak and strong signals. We demonstrate that these two algorithmic features are sufficient conditions to construct a novel word embedding algorithm, Hilbert-MLE. We find that its embeddings obtain equivalent or better performance against other algorithms across 17 intrinsic and extrinsic datasets.
Tasks	Word Embeddings
Published	2019-11-29
URL	https://arxiv.org/abs/1911.13280v1
PDF	https://arxiv.org/pdf/1911.13280v1.pdf
PWC	https://paperswithcode.com/paper/deconstructing-and-reconstructing-word
Repo
Framework

Privacy-Enhancing Fall Detection from Remote Sensor Data Using Multi-Party Computation


Title	Privacy-Enhancing Fall Detection from Remote Sensor Data Using Multi-Party Computation
Authors	Pradip Mainali, Carlton Shepherd
Abstract	Motion-based fall detection systems are concerned with detecting falls from vulnerable users, which is typically performed by classifying measurements from a body-worn inertial measurement unit (IMU) using machine learning. Such systems, however, necessitate the collection of high-resolution measurements that may violate users’ privacy, such as revealing their gait, activities of daily living (ADLs), and relative position using dead reckoning. In this paper, we investigate the application of multi-party computation (MPC) to IMU-based fall detection for protecting device measurement confidentiality. Our system is evaluated in a cloud-based setting that precludes parties from learning the underlying data using multiple, disparate cloud instances deployed in three geographical configurations. Using a publicly-available dataset, we demonstrate that MPC-based fall detection from IMU measurements is practical while achieving state-of-the-art error rates. In the best case, our system executes in 365.2 milliseconds, which falls well within the required time window for on-device data acquisition (750ms).
Tasks
Published	2019-04-22
URL	https://arxiv.org/abs/1904.09896v2
PDF	https://arxiv.org/pdf/1904.09896v2.pdf
PWC	https://paperswithcode.com/paper/providing-confidential-cloud-based-fall
Repo
Framework

Efficient Convolutional Neural Networks for Depth-Based Multi-Person Pose Estimation


Title	Efficient Convolutional Neural Networks for Depth-Based Multi-Person Pose Estimation
Authors	Angel Martínez-González, Michael Villamizar, Olivier Canévet, Jean-Marc Odobez
Abstract	Achieving robust multi-person 2D body landmark localization and pose estimation is essential for human behavior and interaction understanding as encountered for instance in HRI settings. Accurate methods have been proposed recently, but they usually rely on rather deep Convolutional Neural Network (CNN) architecture, thus requiring large computational and training resources. In this paper, we investigate different architectures and methodologies to address these issues and achieve fast and accurate multi-person 2D pose estimation. To foster speed, we propose to work with depth images, whose structure contains sufficient information about body landmarks while being simpler than textured color images and thus potentially requiring less complex CNNs for processing. In this context, we make the following contributions. i) we study several CNN architecture designs combining pose machines relying on the cascade of detectors concept with lightweight and efficient CNN structures; ii) to address the need for large training datasets with high variability, we rely on semi-synthetic data combining multi-person synthetic depth data with real sensor backgrounds; iii) we explore domain adaptation techniques to address the performance gap introduced by testing on real depth images; iv) to increase the accuracy of our fast lightweight CNN models, we investigate knowledge distillation at several architecture levels which effectively enhance performance. Experiments and results on synthetic and real data highlight the impact of our design choices, providing insights into methods addressing standard issues normally faced in practical applications, and resulting in architectures effectively matching our goal in both performance and speed.
Tasks	Domain Adaptation, Multi-Person Pose Estimation, Pose Estimation
Published	2019-12-02
URL	https://arxiv.org/abs/1912.00711v1
PDF	https://arxiv.org/pdf/1912.00711v1.pdf
PWC	https://paperswithcode.com/paper/efficient-convolutional-neural-networks-for-2
Repo
Framework