Paper Group NANR 71
Incorporating Topic Aspects for Online Comment Convincingness Evaluation. Characterizing Interactions and Relationships between People. Deconfounded Lexicon Induction for Interpretable Social Science. A Food Photography App with Image Recognition for Thai Food. Small Coresets to Represent Large Training Data for Support Vector Machines. Analyzing F …
Incorporating Topic Aspects for Online Comment Convincingness Evaluation
| Title | Incorporating Topic Aspects for Online Comment Convincingness Evaluation |
| Authors | Yunfan Gu, Zhongyu Wei, Maoran Xu, Hao Fu, Yang Liu, Xuanjing Huang |
| Abstract | In this paper, we propose to incorporate topic aspects information for online comments convincingness evaluation. Our model makes use of graph convolutional network to utilize implicit topic information within a discussion thread to assist the evaluation of convincingness of each single comment. In order to test the effectiveness of our proposed model, we annotate topic information on top of a public dataset for argument convincingness evaluation. Experimental results show that topic information is able to improve the performance for convincingness evaluation. We also make a move to detect topic aspects automatically. |
| Tasks | Argument Mining |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-5212/ |
| https://www.aclweb.org/anthology/W18-5212 | |
| PWC | https://paperswithcode.com/paper/incorporating-topic-aspects-for-online |
| Repo | |
| Framework | |
Characterizing Interactions and Relationships between People
| Title | Characterizing Interactions and Relationships between People |
| Authors | Farzana Rashid, Eduardo Blanco |
| Abstract | This paper presents a set of dimensions to characterize the association between two people. We distinguish between interactions (when somebody refers to somebody in a conversation) and relationships (a sequence of interactions). We work with dialogue scripts from the TV show Friends, and do not impose any restrictions on the interactions and relationships. We introduce and analyze a new corpus, and present experimental results showing that the task can be automated. |
| Tasks | Question Answering |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1470/ |
| https://www.aclweb.org/anthology/D18-1470 | |
| PWC | https://paperswithcode.com/paper/characterizing-interactions-and-relationships |
| Repo | |
| Framework | |
Deconfounded Lexicon Induction for Interpretable Social Science
| Title | Deconfounded Lexicon Induction for Interpretable Social Science |
| Authors | Reid Pryzant, Kelly Shen, Dan Jurafsky, Stefan Wagner |
| Abstract | NLP algorithms are increasingly used in computational social science to take linguistic observations and predict outcomes like human preferences or actions. Making these social models transparent and interpretable often requires identifying features in the input that predict outcomes while also controlling for potential confounds. We formalize this need as a new task: inducing a lexicon that is predictive of a set of target variables yet uncorrelated to a set of confounding variables. We introduce two deep learning algorithms for the task. The first uses a bifurcated architecture to separate the explanatory power of the text and confounds. The second uses an adversarial discriminator to force confound-invariant text encodings. Both elicit lexicons from learned weights and attentional scores. We use them to induce lexicons that are predictive of timely responses to consumer complaints (controlling for product), enrollment from course descriptions (controlling for subject), and sales from product descriptions (controlling for seller). In each domain our algorithms pick words that are associated with \textit{narrative persuasion}; more predictive and less confound-related than those of standard feature weighting and lexicon induction techniques like regression and log odds. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1146/ |
| https://www.aclweb.org/anthology/N18-1146 | |
| PWC | https://paperswithcode.com/paper/deconfounded-lexicon-induction-for |
| Repo | |
| Framework | |
A Food Photography App with Image Recognition for Thai Food
| Title | A Food Photography App with Image Recognition for Thai Food |
| Authors | Ukrit Tiankaew, Peerapon Chunpongthong, Vacharapat Mettanant |
| Abstract | In this paper, we present a food photography application for smart phones, which can recognise 13 types of Thai food from photos. With this feature, the application can easily help users calculate their calories and make some suggestion, just by keep taking a photo of food they are eating. Our application uses React Native for the front-end, and Python-Flask for the back-end. For image recognition, we design a deep convolutional neural network to learn from our dataset. Moreover, we compare the result of our model with another model adapted from the famous one of Karen Simonyan andAndrew Zisserman called VGG19. We use transfer learning from the pre-trained VGG19, implementing with Keras and Tensorflow. Our result shows that the transfer learning model is better. It give us approximately 82% test accuracy or 18% top-1 error rate. Using top-3 and top-5 scores, The model reports 2.6% top-3 error rate and 1.3% top-5 error rate, which works well in our application. |
| Tasks | Image Recognition, Transfer Learning |
| Published | 2018-07-01 |
| URL | https://ieeexplore.ieee.org/document/8523925 |
| https://www.researchgate.net/publication/328834305_A_Food_Photography_App_with_Image_Recognition_for_Thai_Food | |
| PWC | https://paperswithcode.com/paper/a-food-photography-app-with-image-recognition |
| Repo | |
| Framework | |
Small Coresets to Represent Large Training Data for Support Vector Machines
| Title | Small Coresets to Represent Large Training Data for Support Vector Machines |
| Authors | Cenk Baykal, Murad Tukan, Dan Feldman, Daniela Rus |
| Abstract | Support Vector Machines (SVMs) are one of the most popular algorithms for classification and regression analysis. Despite their popularity, even efficient implementations have proven to be computationally expensive to train at a large-scale, especially in streaming settings. In this paper, we propose a novel coreset construction algorithm for efficiently generating compact representations of massive data sets to speed up SVM training. A coreset is a weighted subset of the original data points such that SVMs trained on the coreset are provably competitive with those trained on the original (massive) data set. We provide both lower and upper bounds on the number of samples required to obtain accurate approximations to the SVM problem as a function of the complexity of the input data. Our analysis also establishes sufficient conditions on the existence of sufficiently compact and representative coresets for the SVM problem. We empirically evaluate the practical effectiveness of our algorithm against synthetic and real-world data sets. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=r1saNM-RW |
| https://openreview.net/pdf?id=r1saNM-RW | |
| PWC | https://paperswithcode.com/paper/small-coresets-to-represent-large-training |
| Repo | |
| Framework | |
Analyzing Filters Toward Efficient ConvNet
| Title | Analyzing Filters Toward Efficient ConvNet |
| Authors | Takumi Kobayashi |
| Abstract | Deep convolutional neural network (ConvNet) is a promising approach for high-performance image classification. The behavior of ConvNet is analyzed mainly based on the neuron activations, such as by visualizing them. In this paper, in contrast to the activations, we focus on filters which are main components of ConvNets. Through analyzing two types of filters at convolution and fully-connected (FC) layers, respectively, on various pre-trained ConvNets, we present the methods to efficiently reformulate the filters, contributing to improving both memory size and classification performance of the ConvNets. They render the filter bases formulated in a parameter-free form as well as the efficient representation for the FC layer. The experimental results on image classification show that the methods are favorably applied to improve various ConvNets, including ResNet, trained on ImageNet with exhibiting high transferability on the other datasets. |
| Tasks | Image Classification |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Kobayashi_Analyzing_Filters_Toward_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Kobayashi_Analyzing_Filters_Toward_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/analyzing-filters-toward-efficient-convnet |
| Repo | |
| Framework | |
The AFRL-Ohio State WMT18 Multimodal System: Combining Visual with Traditional
| Title | The AFRL-Ohio State WMT18 Multimodal System: Combining Visual with Traditional |
| Authors | Jeremy Gwinnup, S, Joshua vick, Michael Hutt, Grant Erdmann, John Duselis, James Davis |
| Abstract | AFRL-Ohio State extends its usage of visual domain-driven machine translation for use as a peer with traditional machine translation systems. As a peer, it is enveloped into a system combination of neural and statistical MT systems to present a composite translation. |
| Tasks | Machine Translation, Multimodal Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6440/ |
| https://www.aclweb.org/anthology/W18-6440 | |
| PWC | https://paperswithcode.com/paper/the-afrl-ohio-state-wmt18-multimodal-system |
| Repo | |
| Framework | |
CrystalFeel at SemEval-2018 Task 1: Understanding and Detecting Emotion Intensity using Affective Lexicons
| Title | CrystalFeel at SemEval-2018 Task 1: Understanding and Detecting Emotion Intensity using Affective Lexicons |
| Authors | Raj Kumar Gupta, Yinping Yang |
| Abstract | While sentiment and emotion analysis has received a considerable amount of research attention, the notion of understanding and detecting the intensity of emotions is relatively less explored. This paper describes a system developed for predicting emotion intensity in tweets. Given a Twitter message, CrystalFeel uses features derived from parts-of-speech, n-grams, word embedding, and multiple affective lexicons including Opinion Lexicon, SentiStrength, AFFIN, NRC Emotion {&} Hash Emotion, and our in-house developed EI Lexicons to predict the degree of the intensity associated with fear, anger, sadness, and joy in the tweet. We found that including the affective lexicons-based features allowed the system to obtain strong prediction performance, while revealing interesting emotion word-level and message-level associations. On gold test data, CrystalFeel obtained Pearson correlations of 0.717 on average emotion intensity and of 0.816 on sentiment intensity. |
| Tasks | Emotion Classification, Emotion Recognition, Sentiment Analysis |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1038/ |
| https://www.aclweb.org/anthology/S18-1038 | |
| PWC | https://paperswithcode.com/paper/crystalfeel-at-semeval-2018-task-1 |
| Repo | |
| Framework | |
A Two-Step Computation of the Exact GAN Wasserstein Distance
| Title | A Two-Step Computation of the Exact GAN Wasserstein Distance |
| Authors | Huidong Liu, Xianfeng GU, Dimitris Samaras |
| Abstract | In this paper, we propose a two-step method to compute the Wasserstein distance in Wasserstein Generative Adversarial Networks (WGANs): 1) The convex part of our objective can be solved by linear programming; 2) The non-convex residual can be approximated by a deep neural network. We theoretically prove that the proposed formulation is equivalent to the discrete Monge-Kantorovich dual formulation. Furthermore, we give the approximation error bound of the Wasserstein distance and the error bound of generalizing the Wasserstein distance from discrete to continuous distributions. Our approach optimizes the exact Wasserstein distance, obviating the need for weight clipping previously used in WGANs. Results on synthetic data show that the our method computes the Wasserstein distance more accurately. Qualitative and quantitative results on MNIST, LSUN and CIFAR-10 datasets show that the proposed method is more efficient than state-of-the-art WGAN methods, and still produces images of comparable quality. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2363 |
| http://proceedings.mlr.press/v80/liu18d/liu18d.pdf | |
| PWC | https://paperswithcode.com/paper/a-two-step-computation-of-the-exact-gan |
| Repo | |
| Framework | |
DiverseNet: When One Right Answer Is Not Enough
| Title | DiverseNet: When One Right Answer Is Not Enough |
| Authors | Michael Firman, Neill D. F. Campbell, Lourdes Agapito, Gabriel J. Brostow |
| Abstract | Many structured prediction tasks in machine vision have a collection of acceptable answers, instead of one definitive ground truth answer. Segmentation of images, for example, is subject to human labeling bias. Similarly, there are multiple possible pixel values that could plausibly complete occluded image regions. State-of-the art supervised learning methods are typically optimized to make a single test-time prediction for each query, failing to find other modes in the output space. Existing methods that allow for sampling often sacrifice speed or accuracy. We introduce a simple method for training a neural network, which enables diverse structured predictions to be made for each test-time query. For a single input, we learn to predict a range of possible answers. We compare favorably to methods that seek diversity through an ensemble of networks. Such stochastic multiple choice learning faces mode collapse, where one or more ensemble members fail to receive any training signal. Our best performing solution can be deployed for various tasks, and just involves small modifications to the existing single-mode architecture, loss function, and training regime. We demonstrate that our method results in quantitative improvements across three challenging tasks: 2D image completion, 3D volume estimation, and flow prediction. |
| Tasks | Structured Prediction |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Firman_DiverseNet_When_One_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Firman_DiverseNet_When_One_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/diversenet-when-one-right-answer-is-not |
| Repo | |
| Framework | |
Single-Image Depth Estimation Based on Fourier Domain Analysis
| Title | Single-Image Depth Estimation Based on Fourier Domain Analysis |
| Authors | Jae-Han Lee, Minhyeok Heo, Kyung-Rae Kim, Chang-Su Kim |
| Abstract | We propose a deep learning algorithm for single-image depth estimation based on the Fourier frequency domain analysis. First, we develop a convolutional neural network structure and propose a new loss function, called depth-balanced Euclidean loss, to train the network reliably for a wide range of depths. Then, we generate multiple depth map candidates by cropping input images with various cropping ratios. In general, a cropped image with a small ratio yields depth details more faithfully, while that with a large ratio provides the overall depth distribution more reliably. To take advantage of these complementary properties, we combine the multiple candidates in the frequency domain. Experimental results demonstrate that proposed algorithm provides the state-of-art performance. Furthermore, through the frequency domain analysis, we validate the efficacy of the proposed algorithm in most frequency bands. |
| Tasks | Depth Estimation |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Lee_Single-Image_Depth_Estimation_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Lee_Single-Image_Depth_Estimation_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/single-image-depth-estimation-based-on |
| Repo | |
| Framework | |
Robust Detection of Adversarial Attacks by Modeling the Intrinsic Properties of Deep Neural Networks
| Title | Robust Detection of Adversarial Attacks by Modeling the Intrinsic Properties of Deep Neural Networks |
| Authors | Zhihao Zheng, Pengyu Hong |
| Abstract | It has been shown that deep neural network (DNN) based classifiers are vulnerable to human-imperceptive adversarial perturbations which can cause DNN classifiers to output wrong predictions with high confidence. We propose an unsupervised learning approach to detect adversarial inputs without any knowledge of attackers. Our approach tries to capture the intrinsic properties of a DNN classifier and uses them to detect adversarial inputs. The intrinsic properties used in this study are the output distributions of the hidden neurons in a DNN classifier presented with natural images. Our approach can be easily applied to any DNN classifiers or combined with other defense strategy to improve robustness. Experimental results show that our approach demonstrates state-of-the-art robustness in defending black-box and gray-box attacks. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8016-robust-detection-of-adversarial-attacks-by-modeling-the-intrinsic-properties-of-deep-neural-networks |
| http://papers.nips.cc/paper/8016-robust-detection-of-adversarial-attacks-by-modeling-the-intrinsic-properties-of-deep-neural-networks.pdf | |
| PWC | https://paperswithcode.com/paper/robust-detection-of-adversarial-attacks-by |
| Repo | |
| Framework | |
Contrastive Learning from Pairwise Measurements
| Title | Contrastive Learning from Pairwise Measurements |
| Authors | Yi Chen, Zhuoran Yang, Yuchen Xie, Princeton Zhaoran Wang |
| Abstract | Learning from pairwise measurements naturally arises from many applications, such as rank aggregation, ordinal embedding, and crowdsourcing. However, most existing models and algorithms are susceptible to potential model misspecification. In this paper, we study a semiparametric model where the pairwise measurements follow a natural exponential family distribution with an unknown base measure. Such a semiparametric model includes various popular parametric models, such as the Bradley-Terry-Luce model and the paired cardinal model, as special cases. To estimate this semiparametric model without specifying the base measure, we propose a data augmentation technique to create virtual examples, which enables us to define a contrastive estimator. In particular, we prove that such a contrastive estimator is invariant to model misspecification within the natural exponential family, and moreover, attains the optimal statistical rate of convergence up to a logarithmic factor. We provide numerical experiments to corroborate our theory. |
| Tasks | Data Augmentation |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8288-contrastive-learning-from-pairwise-measurements |
| http://papers.nips.cc/paper/8288-contrastive-learning-from-pairwise-measurements.pdf | |
| PWC | https://paperswithcode.com/paper/contrastive-learning-from-pairwise |
| Repo | |
| Framework | |
Deeply Learned Compositional Models for Human Pose Estimation
| Title | Deeply Learned Compositional Models for Human Pose Estimation |
| Authors | Wei Tang, Pei Yu, Ying Wu |
| Abstract | Compositional models represent patterns with hierarchies of meaningful parts and subparts. Their ability to characterize high-order relationships among body parts helps resolve low-level ambiguities in human pose estimation (HPE). However, prior compositional models make unrealistic assumptions on subpart-part relationships, making them incapable to characterize complex compositional patterns. Moreover, state spaces of their higher-level parts can be exponentially large, complicating both inference and learning. To address these issues, this paper introduces a novel framework, termed as Deeply Learned Compositional Model (DLCM), for HPE. It exploits deep neural networks to learn the compositionality of human bodies. This results in a network with a hierarchical compositional architecture and bottom-up/top-down inference stages. In addition, we propose a novel bone-based part representation. It not only compactly encodes orientations, scales and shapes of parts, but also avoids their potentially large state spaces. With significantly lower complexities, our approach outperforms state-of-the-art methods on three benchmark datasets. |
| Tasks | Pose Estimation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Wei_Tang_Deeply_Learned_Compositional_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Wei_Tang_Deeply_Learned_Compositional_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deeply-learned-compositional-models-for-human |
| Repo | |
| Framework | |
Parametric Information Bottleneck to Optimize Stochastic Neural Networks
| Title | Parametric Information Bottleneck to Optimize Stochastic Neural Networks |
| Authors | Thanh T. Nguyen, Jaesik Choi |
| Abstract | In this paper, we present a layer-wise learning of stochastic neural networks (SNNs) in an information-theoretic perspective. In each layer of an SNN, the compression and the relevance are defined to quantify the amount of information that the layer contains about the input space and the target space, respectively. We jointly optimize the compression and the relevance of all parameters in an SNN to better exploit the neural network’s representation. Previously, the Information Bottleneck (IB) framework (\cite{Tishby99}) extracts relevant information for a target variable. Here, we propose Parametric Information Bottleneck (PIB) for a neural network by utilizing (only) its model parameters explicitly to approximate the compression and the relevance. We show that, as compared to the maximum likelihood estimate (MLE) principle, PIBs : (i) improve the generalization of neural networks in classification tasks, (ii) push the representation of neural networks closer to the optimal information-theoretical representation in a faster manner. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=ByED-X-0W |
| https://openreview.net/pdf?id=ByED-X-0W | |
| PWC | https://paperswithcode.com/paper/parametric-information-bottleneck-to-optimize |
| Repo | |
| Framework | |
