October 16, 2019

2305 words 11 mins read

Paper Group NAWR 10

Paper Group NAWR 10

Semantically Equivalent Adversarial Rules for Debugging NLP models. LiDo RDF: From a Relational Database to a Linked Data Graph of Linguistic Terms and Bibliographic Data. MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Frame Interpolation and Enhancement. Resource Interoperability for Sustainable Benchmarking: T …

Semantically Equivalent Adversarial Rules for Debugging NLP models

Title Semantically Equivalent Adversarial Rules for Debugging NLP models
Authors Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin
Abstract Complex machine learning models for NLP are often brittle, making different predictions for input instances that are extremely similar semantically. To automatically detect this behavior for individual instances, we present semantically equivalent adversaries (SEAs) {–} semantic-preserving perturbations that induce changes in the model{'}s predictions. We generalize these adversaries into semantically equivalent adversarial rules (SEARs) {–} simple, universal replacement rules that induce adversaries on many instances. We demonstrate the usefulness and flexibility of SEAs and SEARs by detecting bugs in black-box state-of-the-art models for three domains: machine comprehension, visual question-answering, and sentiment analysis. Via user studies, we demonstrate that we generate high-quality local adversaries for more instances than humans, and that SEARs induce four times as many mistakes as the bugs discovered by human experts. SEARs are also actionable: retraining models using data augmentation significantly reduces bugs, while maintaining accuracy.
Tasks Data Augmentation, Question Answering, Reading Comprehension, Sentiment Analysis, Visual Question Answering
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-1079/
PDF https://www.aclweb.org/anthology/P18-1079
PWC https://paperswithcode.com/paper/semantically-equivalent-adversarial-rules-for
Repo https://github.com/marcotcr/sears
Framework tf

LiDo RDF: From a Relational Database to a Linked Data Graph of Linguistic Terms and Bibliographic Data

Title LiDo RDF: From a Relational Database to a Linked Data Graph of Linguistic Terms and Bibliographic Data
Authors Bettina Klimek, Robert Sch{"a}dlich, Dustin Kr{"o}ger, Edwin Knese, Benedikt El{\ss}mann
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1386/
PDF https://www.aclweb.org/anthology/L18-1386
PWC https://paperswithcode.com/paper/lido-rdf-from-a-relational-database-to-a
Repo https://github.com/AKSW/lido2rdf
Framework none

MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Frame Interpolation and Enhancement

Title MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Frame Interpolation and Enhancement
Authors Wenbo Bao, Wei-Sheng Lai, Xiaoyun Zhang, Zhiyong Gao, Ming-Hsuan Yang
Abstract Motion estimation (ME) and motion compensation (MC) have dominated classical video frame interpolation systems over the past decades. Recently, the convolutional neural networks set up a new data-driven paradigm for frame interpolation. However, existing learning based methods typically fall into estimating only one of the ME and MC building blocks, resulting in a limited performance on both computational efficiency and interpolation accuracy. In this work, we propose a motion estimation and motion compensation driven neural network for video frame interpolation. A novel adaptive warping layer is proposed to integrate both optical flow and interpolation kernels to synthesize target frame pixels. This layer is fully differentiable such that both the flow and kernel estimation networks can be optimized jointly. Our method benefits from the ME and MC model-driven architecture while avoiding the conventional hand-crafted design by training on a large amount of video data. Compared to existing methods, our approach is computationally efficient and able to generate more visually appealing results. Moreover, our MEMC architecture is a general framework, which can be seamlessly adapted to several video enhancement tasks, e.g., super-resolution, denoising, and deblocking. Extensive quantitative and qualitative evaluations demonstrate that the proposed method performs favorably against the state-of-the-art video frame interpolation and enhancement algorithms on a wide range of datasets.
Tasks Denoising, Motion Compensation, Motion Estimation, Optical Flow Estimation, Super-Resolution, Video Frame Interpolation
Published 2018-10-20
URL https://arxiv.org/abs/1810.08768
PDF https://arxiv.org/pdf/1810.08768
PWC https://paperswithcode.com/paper/memc-net-motion-estimation-and-motion-1
Repo https://github.com/baowenbo/MEMC-Net
Framework pytorch

Resource Interoperability for Sustainable Benchmarking: The Case of Events

Title Resource Interoperability for Sustainable Benchmarking: The Case of Events
Authors Chantal van Son, Oana Inel, Roser Morante, Lora Aroyo, Piek Vossen
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1178/
PDF https://www.aclweb.org/anthology/L18-1178
PWC https://paperswithcode.com/paper/resource-interoperability-for-sustainable
Repo https://github.com/ChantalvanSon/CorpusComparison
Framework none

Talking about other people: an endless range of possibilities

Title Talking about other people: an endless range of possibilities
Authors Emiel van Miltenburg, Desmond Elliott, Piek Vossen
Abstract Image description datasets, such as Flickr30K and MS COCO, show a high degree of variation in the ways that crowd-workers talk about the world. Although this gives us a rich and diverse collection of data to work with, it also introduces uncertainty about how the world should be described. This paper shows the extent of this uncertainty in the PEOPLE-domain. We present a taxonomy of different ways to talk about other people. This taxonomy serves as a reference point to think about how other people should be described, and can be used to classify and compute statistics about labels applied to people.
Tasks Text Generation
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-6550/
PDF https://www.aclweb.org/anthology/W18-6550
PWC https://paperswithcode.com/paper/talking-about-other-people-an-endless-range
Repo https://github.com/evanmiltenburg/LabelingPeople
Framework none

Seq2seq Dependency Parsing

Title Seq2seq Dependency Parsing
Authors Zuchao Li, Jiaxun Cai, Shexia He, Hai Zhao
Abstract This paper presents a sequence to sequence (seq2seq) dependency parser by directly predicting the relative position of head for each given word, which therefore results in a truly end-to-end seq2seq dependency parser for the first time. Enjoying the advantage of seq2seq modeling, we enrich a series of embedding enhancement, including firstly introduced subword and node2vec augmentation. Meanwhile, we propose a beam search decoder with tree constraint and subroot decomposition over the sequence to furthermore enhance our seq2seq parser. Our parser is evaluated on benchmark treebanks, being on par with the state-of-the-art parsers by achieving 94.11{%} UAS on PTB and 88.78{%} UAS on CTB, respectively.
Tasks Dependency Parsing, Feature Engineering
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1271/
PDF https://www.aclweb.org/anthology/C18-1271
PWC https://paperswithcode.com/paper/seq2seq-dependency-parsing
Repo https://github.com/bcmi220/seq2seq_parser
Framework pytorch

Automatically Creating a Lexicon of Verbal Polarity Shifters: Mono- and Cross-lingual Methods for German

Title Automatically Creating a Lexicon of Verbal Polarity Shifters: Mono- and Cross-lingual Methods for German
Authors Marc Schulder, Michael Wiegand, Josef Ruppenhofer
Abstract
Tasks Sentiment Analysis
Published 2018-08-01
URL https://www.aclweb.org/anthology/papers/C18-1213/c18-1213
PDF https://www.aclweb.org/anthology/C18-1213
PWC https://paperswithcode.com/paper/automatically-creating-a-lexicon-of-verbal
Repo https://github.com/uds-lsv/coling2018
Framework none

Evaluating Shallow and Deep Neural Networks for Network Intrusion Detection Systems in Cyber Security

Title Evaluating Shallow and Deep Neural Networks for Network Intrusion Detection Systems in Cyber Security
Authors Rahul-Vigneswaran K, Vinayakumar R, Soman KP, Prabaharan Poornachandran
Abstract Intrusion detection system (IDS) has become an essential layer in all the latest ICT system due to an urge towards cyber safety in the day-to-day world. Reasons including uncertainty in finding the types of attacks and increased the complexity of advanced cyber attacks, IDS calls for the need of integration of Deep Neural Networks (DNNs). In this paper, DNNs have been utilized to predict the attacks on Network Intrusion Detection System (N-IDS). A DNN with 0.1 rate of learning is applied and is run for 1000 number of epochs and KDDCup-`99’ dataset has been used for training and benchmarking the network. For comparison purposes, the training is done on the same dataset with several other classical machine learning algorithms and DNN of layers ranging from 1 to 5. The results were compared and concluded that a DNN of 3 layers has superior performance over all the other classical machine learning algorithms. |
Tasks Intrusion Detection, Network Intrusion Detection
Published 2018-10-08
URL https://rahulvigneswaran.github.io/publication/2018-10-01-Evaluating%20Shallow%20and%20Deep%20Neural%20Networks%20for%20Network%20Intrusion%20Detection%20Systems%20in%20Cyber%20Security-1
PDF https://ieeexplore.ieee.org/abstract/document/8494096
PWC https://paperswithcode.com/paper/evaluating-shallow-and-deep-neural-networks
Repo https://github.com/rahulvigneswaran/Intrusion-Detection-Systems
Framework none

Creating Large-Scale Multilingual Cognate Tables

Title Creating Large-Scale Multilingual Cognate Tables
Authors Winston Wu, David Yarowsky
Abstract
Tasks Machine Translation, Semantic Textual Similarity, Transliteration
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1538/
PDF https://www.aclweb.org/anthology/L18-1538
PWC https://paperswithcode.com/paper/creating-large-scale-multilingual-cognate
Repo https://github.com/wswu/coglust
Framework none

Structure-Aware Convolutional Neural Networks

Title Structure-Aware Convolutional Neural Networks
Authors Jianlong Chang, Jie Gu, Lingfeng Wang, Gaofeng Meng, Shiming Xiang, Chunhong Pan
Abstract Convolutional neural networks (CNNs) are inherently subject to invariable filters that can only aggregate local inputs with the same topological structures. It causes that CNNs are allowed to manage data with Euclidean or grid-like structures (e.g., images), not ones with non-Euclidean or graph structures (e.g., traffic networks). To broaden the reach of CNNs, we develop structure-aware convolution to eliminate the invariance, yielding a unified mechanism of dealing with both Euclidean and non-Euclidean structured data. Technically, filters in the structure-aware convolution are generalized to univariate functions, which are capable of aggregating local inputs with diverse topological structures. Since infinite parameters are required to determine a univariate function, we parameterize these filters with numbered learnable parameters in the context of the function approximation theory. By replacing the classical convolution in CNNs with the structure-aware convolution, Structure-Aware Convolutional Neural Networks (SACNNs) are readily established. Extensive experiments on eleven datasets strongly evidence that SACNNs outperform current models on various machine learning tasks, including image classification and clustering, text categorization, skeleton-based action recognition, molecular activity detection, and taxi flow prediction.
Tasks Action Detection, Activity Detection, Image Classification, Skeleton Based Action Recognition, Temporal Action Localization, Text Categorization
Published 2018-12-01
URL http://papers.nips.cc/paper/7287-structure-aware-convolutional-neural-networks
PDF http://papers.nips.cc/paper/7287-structure-aware-convolutional-neural-networks.pdf
PWC https://paperswithcode.com/paper/structure-aware-convolutional-neural-networks
Repo https://github.com/vector-1127/SACNNs
Framework tf

C-HTS: A Concept-based Hierarchical Text Segmentation approach

Title C-HTS: A Concept-based Hierarchical Text Segmentation approach
Authors Mostafa Bayomi, S{'e}amus Lawless
Abstract
Tasks Information Retrieval, Question Answering, Text Summarization
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1241/
PDF https://www.aclweb.org/anthology/L18-1241
PWC https://paperswithcode.com/paper/c-hts-a-concept-based-hierarchical-text
Repo https://github.com/bayomim/C-HTS
Framework none

Efficient Relative Attribute Learning using Graph Neural Networks

Title Efficient Relative Attribute Learning using Graph Neural Networks
Authors Zihang Meng, Nagesh Adluru, Hyunwoo J. Kim, Glenn Fung, Vikas Singh
Abstract A sizable body of work on relative attributes provides compelling evidence that relating pairs of images along a continuum of strength pertaining to a visual attribute yields significant improvements in a wide variety of tasks in vision. In this paper, we show how emerging ideas in graph neural networks can yield a unified solution to various problems that broadly fall under relative attribute learning. Our main idea is the realization that relative attribute learning naturally benefits from exploiting the graphical structure of dependencies among the different relative attributes of images, especially when only partial ordering of the relative attributes is provided in the training data. We use message passing on a probabilistic graphical model to perform end to end learning of appropriate representations of the images, their relationships as well as the interplay between different attributes to best align with provided annotations. Our experiments demonstrate that this simple end-to-end learning framework using GNNs is very effective in achieving competitive accuracy with specialized methods for both relative attribute learning and binary attribute prediction, while significantly relaxing the requirements on the training data and/or the number of parameters or both.
Tasks
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Zihang_Meng_Efficient_Relative_Attribute_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Zihang_Meng_Efficient_Relative_Attribute_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/efficient-relative-attribute-learning-using
Repo https://github.com/zihangm/RAL_GNN
Framework tf

Matrix capsules with EM routing

Title Matrix capsules with EM routing
Authors Geoffrey E Hinton, Sara Sabour, Nicholas Frosst
Abstract A capsule is a group of neurons whose outputs represent different properties of the same entity. Each layer in a capsule network contains many capsules. We describe a version of capsules in which each capsule has a logistic unit to represent the presence of an entity and a 4x4 matrix which could learn to represent the relationship between that entity and the viewer (the pose). A capsule in one layer votes for the pose matrix of many different capsules in the layer above by multiplying its own pose matrix by trainable viewpoint-invariant transformation matrices that could learn to represent part-whole relationships. Each of these votes is weighted by an assignment coefficient. These coefficients are iteratively updated for each image using the Expectation-Maximization algorithm such that the output of each capsule is routed to a capsule in the layer above that receives a cluster of similar votes. The transformation matrices are trained discriminatively by backpropagating through the unrolled iterations of EM between each pair of adjacent capsule layers. On the smallNORB benchmark, capsules reduce the number of test errors by 45% compared to the state-of-the-art. Capsules also show far more resistance to white box adversarial attacks than our baseline convolutional neural network.
Tasks
Published 2018-01-01
URL https://openreview.net/forum?id=HJWLfGWRb
PDF https://openreview.net/pdf?id=HJWLfGWRb
PWC https://paperswithcode.com/paper/matrix-capsules-with-em-routing
Repo https://github.com/IBM/matrix-capsules-with-em-routing
Framework tf

Attributed and Predictive Entity Embedding for Fine-Grained Entity Typing in Knowledge Bases

Title Attributed and Predictive Entity Embedding for Fine-Grained Entity Typing in Knowledge Bases
Authors Hailong Jin, Lei Hou, Juanzi Li, Tiansi Dong
Abstract Fine-grained entity typing aims at identifying the semantic type of an entity in KB. Type information is very important in knowledge bases, but are unfortunately incomplete even in some large knowledge bases. Limitations of existing methods are either ignoring the structure and type information in KB or requiring large scale annotated corpus. To address these issues, we propose an attributed and predictive entity embedding method, which can fully utilize various kinds of information comprehensively. Extensive experiments on two real DBpedia datasets show that our proposed method significantly outperforms 8 state-of-the-art methods, with 4.0{%} and 5.2{%} improvement in Mi-F1 and Ma-F1, respectively.
Tasks Entity Linking, Entity Typing, Knowledge Base Completion, Question Answering, Relation Extraction
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1024/
PDF https://www.aclweb.org/anthology/C18-1024
PWC https://paperswithcode.com/paper/attributed-and-predictive-entity-embedding
Repo https://github.com/Tsinghua-PhD/APE
Framework none

Interpretable Basis Decomposition for Visual Explanation

Title Interpretable Basis Decomposition for Visual Explanation
Authors Bolei Zhou, Yiyou Sun, David Bau, Antonio Torralba
Abstract Explanations of the decisions made by a deep neural network are important for human end-users to be able to understand and diagnose the trustworthiness of the system. Current neural networks used for visual recognition are generally used as black boxes that do not provide any human interpretable justification for a prediction. In this work we propose a new framework called Interpretable Basis Decomposition for providing visual explanations for classification networks. By decomposing the neural activations of the input image into semantically interpretable components pre-trained from a large concept corpus, the proposed framework is able to disentangle the evidence encoded in the activation feature vector, and quantify the contribution of each piece of evidence to the final prediction. We apply our framework for providing explanations to several popular networks for visual recognition, and show it is able to explain the predictions given by the networks in human-interpretable way. The human interpretability of the visual explanations provided by our framework and other recent explanation methods is evaluated through Amazon Mechanical Turk, showing that our framework generates more faithful and interpretable explanations.
Tasks
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Antonio_Torralba_Interpretable_Basis_Decomposition_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Antonio_Torralba_Interpretable_Basis_Decomposition_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/interpretable-basis-decomposition-for-visual
Repo https://github.com/CSAILVision/IBD
Framework pytorch
comments powered by Disqus