Paper Group NANR 257
LEARNING ADVERSARIAL EXAMPLES WITH RIEMANNIAN GEOMETRY. mID: Tracking and Identifying People with Millimeter Wave Radar. A Knowledge Regularized Hierarchical Approach for Emotion Cause Analysis. Tweaks and Tricks for Word Embedding Disruptions. Guess Who’s Coming (and Who’s Going): Bringing Perspective to the Rational Speech Acts Framework. Learnin …
LEARNING ADVERSARIAL EXAMPLES WITH RIEMANNIAN GEOMETRY
| Title | LEARNING ADVERSARIAL EXAMPLES WITH RIEMANNIAN GEOMETRY |
| Authors | Shufei Zhang, Kaizhu Huang, Rui Zhang, Amir Hussain |
| Abstract | Adversarial examples, referred to as augmented data points generated by imperceptible perturbation of input samples, have recently drawn much attention. Well-crafted adversarial examples may even mislead state-of-the-art deep models to make wrong predictions easily. To alleviate this problem, many studies focus on investigating how adversarial examples can be generated and/or resisted. All the existing work handles this problem in the Euclidean space, which may however be unable to describe data geometry. In this paper, we propose a generalized framework that addresses the learning problem of adversarial examples with Riemannian geometry. Specifically, we define the local coordinate systems on Riemannian manifold, develop a novel model called Adversarial Training with Riemannian Manifold, and design a series of theory that manages to learn the adversarial examples in the Riemannian space feasibly and efficiently. The proposed work is important in that (1) it is a generalized learning methodology since Riemmanian manifold space would be degraded to the Euclidean space in a special case; (2) it is the first work to tackle the adversarial example problem tractably through the perspective of geometry; (3) from the perspective of geometry, our method leads to the steepest direction of the loss function. We also provide a series of theory showing that our proposed method can truly find the decent direction for the loss function with a comparable computational time against traditional adversarial methods. Finally, the proposed framework demonstrates superior performance to the traditional counterpart methods on benchmark data including MNIST, CIFAR-10 and SVHN. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=H1lADsCcFQ |
| https://openreview.net/pdf?id=H1lADsCcFQ | |
| PWC | https://paperswithcode.com/paper/learning-adversarial-examples-with-riemannian |
| Repo | |
| Framework | |
mID: Tracking and Identifying People with Millimeter Wave Radar
| Title | mID: Tracking and Identifying People with Millimeter Wave Radar |
| Authors | Peijun Zhao, Chris Xiaoxuan Lu, Jianan Wang, Changhao Chen, Wei Wang, Niki Trigoni, and Andrew Markham |
| Abstract | The key to offering personalised services in smart spaces is knowing where a particular person is with a high degree of accuracy. Visual tracking is one such solution, but concerns arise around the potential leakage of raw video information and many people are not comfortable accepting cameras in their homes or workplaces. We propose a human tracking and identification system (mID) based on millimeter wave radar which has a high tracking accuracy, without being visually compromising. Unlike competing techniques based on WiFi Channel State Information (CSI), it is capable of tracking and identifying multiple people simultaneously. Using a lowcost, commercial, off-the-shelf radar, we first obtain sparse point clouds and form temporally associated trajectories. With the aid of a deep recurrent network, we identify individual users. We evaluate and demonstrate our system across a variety of scenarios, showing median position errors of 0.16 m and identification accuracy of 89% for 12 people. |
| Tasks | RF-based Visual Tracking, Visual Tracking |
| Published | 2019-05-29 |
| URL | https://doi.org/10.1109/DCOSS.2019.00028 |
| http://www.cs.ox.ac.uk/files/10889/%5BDCOSS19%5DmID.pdf | |
| PWC | https://paperswithcode.com/paper/mid-tracking-and-identifying-people-with |
| Repo | |
| Framework | |
A Knowledge Regularized Hierarchical Approach for Emotion Cause Analysis
| Title | A Knowledge Regularized Hierarchical Approach for Emotion Cause Analysis |
| Authors | Chuang Fan, Hongyu Yan, Jiachen Du, Lin Gui, Lidong Bing, Min Yang, Ruifeng Xu, Ruibin Mao |
| Abstract | Emotion cause analysis, which aims to identify the reasons behind emotions, is a key topic in sentiment analysis. A variety of neural network models have been proposed recently, however, these previous models mostly focus on the learning architecture with local textual information, ignoring the discourse and prior knowledge, which play crucial roles in human text comprehension. In this paper, we propose a new method to extract emotion cause with a hierarchical neural model and knowledge-based regularizations, which aims to incorporate discourse context information and restrain the parameters by sentiment lexicon and common knowledge. The experimental results demonstrate that our proposed method achieves the state-of-the-art performance on two public datasets in different languages (Chinese and English), outperforming a number of competitive baselines by at least 2.08{%} in F-measure. |
| Tasks | Reading Comprehension, Sentiment Analysis |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1563/ |
| https://www.aclweb.org/anthology/D19-1563 | |
| PWC | https://paperswithcode.com/paper/a-knowledge-regularized-hierarchical-approach |
| Repo | |
| Framework | |
Tweaks and Tricks for Word Embedding Disruptions
| Title | Tweaks and Tricks for Word Embedding Disruptions |
| Authors | Amir Hazem, Hern, Nicolas ez |
| Abstract | Word embeddings are established as very effective models used in several NLP applications. If they differ in their architecture and training process, they often exhibit similar properties and remain vector space models with continuously-valued dimensions describing the observed data. The complexity resides in the developed strategies for learning the values within each dimensional space. In this paper, we introduce the concept of disruption which we define as a side effect of the training process of embedding models. Disruptions are viewed as a set of embedding values that are more likely to be noise than effective descriptive features. We show that dealing with disruption phenomenon is of a great benefit to bottom-up sentence embedding representation. By contrasting several in-domain and pre-trained embedding models, we propose two simple but very effective tweaking techniques that yield strong empirical improvements on textual similarity task. |
| Tasks | Sentence Embedding, Word Embeddings |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1054/ |
| https://www.aclweb.org/anthology/R19-1054 | |
| PWC | https://paperswithcode.com/paper/tweaks-and-tricks-for-word-embedding |
| Repo | |
| Framework | |
Guess Who’s Coming (and Who’s Going): Bringing Perspective to the Rational Speech Acts Framework
| Title | Guess Who’s Coming (and Who’s Going): Bringing Perspective to the Rational Speech Acts Framework |
| Authors | Carolyn Jane Anderson, Brian W. Dillon |
| Abstract | |
| Tasks | Bayesian Inference |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0119/ |
| https://www.aclweb.org/anthology/W19-0119 | |
| PWC | https://paperswithcode.com/paper/guess-whos-coming-and-whos-going-bringing |
| Repo | |
| Framework | |
Learning in Generalized Linear Contextual Bandits with Stochastic Delays
| Title | Learning in Generalized Linear Contextual Bandits with Stochastic Delays |
| Authors | Zhengyuan Zhou, Renyuan Xu, Jose Blanchet |
| Abstract | In this paper, we consider online learning in generalized linear contextual bandits where rewards are not immediately observed. Instead, rewards are available to the decision maker only after some delay, which is unknown and stochastic, even though a decision must be made at each time step for an incoming set of contexts. We study the performance of upper confidence bound (UCB) based algorithms adapted to this delayed setting. In particular, we design a delay-adaptive algorithm, which we call Delayed UCB, for generalized linear contextual bandits using UCB-style exploration and establish regret bounds under various delay assumptions. In the important special case of linear contextual bandits, we further modify this algorithm and establish a tighter regret bound under the same delay assumptions. Our results contribute to the broad landscape of contextual bandits literature by establishing that UCB algorithms, which are widely deployed in modern recommendation engines, can be made robust to delays. |
| Tasks | Multi-Armed Bandits |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8762-learning-in-generalized-linear-contextual-bandits-with-stochastic-delays |
| http://papers.nips.cc/paper/8762-learning-in-generalized-linear-contextual-bandits-with-stochastic-delays.pdf | |
| PWC | https://paperswithcode.com/paper/learning-in-generalized-linear-contextual |
| Repo | |
| Framework | |
Graph Transformer
| Title | Graph Transformer |
| Authors | Yuan Li, Xiaodan Liang, Zhiting Hu, Yinbo Chen, Eric P. Xing |
| Abstract | Graph neural networks (GNN) have gained increasing research interests as a mean to the challenging goal of robust and universal graph learning. Previous GNNs have assumed single pre-fixed graph structure and permitted only local context encoding. This paper proposes a novel Graph Transformer (GTR) architecture that captures long-range dependency with global attention, and enables dynamic graph structures. In particular, GTR propagates features within the same graph structure via an intra-graph message passing, and transforms dynamic semantics across multi-domain graph-structured data (e.g. images, sequences, knowledge graphs) for multi-modal learning via an inter-graph message passing. Furthermore, GTR enables effective incorporation of any prior graph structure by weighted averaging of the prior and learned edges, which can be crucially useful for scenarios where prior knowledge is desired. The proposed GTR achieves new state-of-the-arts across three benchmark tasks, including few-shot learning, medical abnormality and disease classification, and graph classification. Experiments show that GTR is superior in learning robust graph representations, transforming high-level semantics across domains, and bridging between prior graph structure with automatic structure learning. |
| Tasks | Few-Shot Learning, Graph Classification, Knowledge Graphs |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HJei-2RcK7 |
| https://openreview.net/pdf?id=HJei-2RcK7 | |
| PWC | https://paperswithcode.com/paper/graph-transformer |
| Repo | |
| Framework | |
Brenda Starr at SemEval-2019 Task 4: Hyperpartisan News Detection
| Title | Brenda Starr at SemEval-2019 Task 4: Hyperpartisan News Detection |
| Authors | Olga Papadopoulou, Giorgos Kordopatis-Zilos, Markos Zampoglou, Symeon Papadopoulos, Yiannis Kompatsiaris |
| Abstract | In the effort to tackle the challenge of Hyperpartisan News Detection, i.e., the task of deciding whether a news article is biased towards one party, faction, cause, or person, we experimented with two systems: i) a standard supervised learning approach using superficial text and bag-of-words features from the article title and body, and ii) a deep learning system comprising a four-layer convolutional neural network and max-pooling layers after the embedding layer, feeding the consolidated features to a bi-directional recurrent neural network. We achieved an F-score of 0.712 with our best approach, which corresponds to the mid-range of performance levels in the leaderboard. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2157/ |
| https://www.aclweb.org/anthology/S19-2157 | |
| PWC | https://paperswithcode.com/paper/brenda-starr-at-semeval-2019-task-4 |
| Repo | |
| Framework | |
Zero-shot transfer for implicit discourse relation classification
| Title | Zero-shot transfer for implicit discourse relation classification |
| Authors | Murathan Kurfal{\i}, Robert {"O}stling |
| Abstract | Automatically classifying the relation between sentences in a discourse is a challenging task, in particular when there is no overt expression of the relation. It becomes even more challenging by the fact that annotated training data exists only for a small number of languages, such as English and Chinese. We present a new system using zero-shot transfer learning for implicit discourse relation classification, where the only resource used for the target language is unannotated parallel text. This system is evaluated on the discourse-annotated TED-MDB parallel corpus, where it obtains good results for all seven languages using only English training data. |
| Tasks | Implicit Discourse Relation Classification, Relation Classification, Transfer Learning |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-5927/ |
| https://www.aclweb.org/anthology/W19-5927 | |
| PWC | https://paperswithcode.com/paper/zero-shot-transfer-for-implicit-discourse-1 |
| Repo | |
| Framework | |
Encoder-decoder models for latent phonological representations of words
| Title | Encoder-decoder models for latent phonological representations of words |
| Authors | Cass Jacobs, ra L., Fred Mailhot |
| Abstract | We use sequence-to-sequence networks trained on sequential phonetic encoding tasks to construct compositional phonological representations of words. We show that the output of an encoder network can predict the phonetic durations of American English words better than a number of alternative forms. We also show that the model{'}s learned representations map onto existing measures of words{'} phonological structure (phonological neighborhood density and phonotactic probability). |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4224/ |
| https://www.aclweb.org/anthology/W19-4224 | |
| PWC | https://paperswithcode.com/paper/encoder-decoder-models-for-latent |
| Repo | |
| Framework | |
StereoDRNet: Dilated Residual StereoNet
| Title | StereoDRNet: Dilated Residual StereoNet |
| Authors | Rohan Chabra, Julian Straub, Christopher Sweeney, Richard Newcombe, Henry Fuchs |
| Abstract | We propose a system that uses a convolution neural network (CNN) to estimate depth from a stereo pair followed by volumetric fusion of the predicted depth maps to produce a 3D reconstruction of a scene. Our proposed depth refinement architecture, predicts view-consistent disparity and occlusion maps that helps the fusion system to produce geometrically consistent reconstructions. We utilize 3D dilated convolutions in our proposed cost filtering network that yields better filtering while almost halving the computational cost in comparison to state of the art cost filtering architectures. For feature extraction we use the Vortex Pooling architecture. The proposed method achieves state of the art results in KITTI 2012, KITTI 2015 and ETH 3D stereo benchmarks. Finally, we demonstrate that our system is able to produce high fidelity 3D scene reconstructions that outperforms the state of the art stereo system. |
| Tasks | 3D Reconstruction |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Chabra_StereoDRNet_Dilated_Residual_StereoNet_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Chabra_StereoDRNet_Dilated_Residual_StereoNet_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/stereodrnet-dilated-residual-stereonet |
| Repo | |
| Framework | |
Harvey Mudd College at SemEval-2019 Task 4: The D.X. Beaumont Hyperpartisan News Detector
| Title | Harvey Mudd College at SemEval-2019 Task 4: The D.X. Beaumont Hyperpartisan News Detector |
| Authors | Evan Amason, Jake Palanker, Mary Clare Shen, Julie Medero |
| Abstract | We use the 600 hand-labelled articles from SemEval Task 4 to hand-tune a classifier with 3000 features for the Hyperpartisan News Detection task. Our final system uses features based on bag-of-words (BoW), analysis of the article title, language complexity, and simple sentiment analysis in a naive Bayes classifier. We trained our final system on the 600,000 articles labelled by publisher. Our final system has an accuracy of 0.653 on the hand-labeled test set. The most effective features are the Automated Readability Index and the presence of certain words in the title. This suggests that hyperpartisan writing uses a distinct writing style, especially in the title. |
| Tasks | Sentiment Analysis |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2166/ |
| https://www.aclweb.org/anthology/S19-2166 | |
| PWC | https://paperswithcode.com/paper/harvey-mudd-college-at-semeval-2019-task-4-2 |
| Repo | |
| Framework | |
NLP@UIT at SemEval-2019 Task 4: The Paparazzo Hyperpartisan News Detector
| Title | NLP@UIT at SemEval-2019 Task 4: The Paparazzo Hyperpartisan News Detector |
| Authors | Duc-Vu Nguyen, Thin Dang, Ngan Nguyen |
| Abstract | This paper describes the system of NLP@UIT that participated in Task 4 of SemEval-2019. We developed a system that predicts whether an English news article follows a hyperpartisan argumentation. Paparazzo is the name of our system and is also the code name of our team in Task 4 of SemEval-2019. The Paparazzo system, in which we use tri-grams of words and hepta-grams of characters, officially ranks thirteen with an accuracy of 0.747. Another system of ours, which utilizes trigrams of words, tri-grams of characters, trigrams of part-of-speech, syntactic dependency sub-trees, and named-entity recognition tags, achieved an accuracy of 0.787 and is proposed after the deadline of Task 4. |
| Tasks | Named Entity Recognition |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2167/ |
| https://www.aclweb.org/anthology/S19-2167 | |
| PWC | https://paperswithcode.com/paper/nlpuit-at-semeval-2019-task-4-the-paparazzo |
| Repo | |
| Framework | |
Context-aware Neural Machine Translation with Coreference Information
| Title | Context-aware Neural Machine Translation with Coreference Information |
| Authors | Takumi Ohtani, Hidetaka Kamigaito, Masaaki Nagata, Manabu Okumura |
| Abstract | We present neural machine translation models for translating a sentence in a text by using a graph-based encoder which can consider coreference relations provided within the text explicitly. The graph-based encoder can dynamically encode the source text without attending to all tokens in the text. In experiments, our proposed models provide statistically significant improvement to the previous approach of at most 0.9 points in the BLEU score on the OpenSubtitle2018 English-to-Japanese data set. Experimental results also show that the graph-based encoder can handle a longer text well, compared with the previous approach. |
| Tasks | Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6505/ |
| https://www.aclweb.org/anthology/D19-6505 | |
| PWC | https://paperswithcode.com/paper/context-aware-neural-machine-translation-with |
| Repo | |
| Framework | |
Rouletabille at SemEval-2019 Task 4: Neural Network Baseline for Identification of Hyperpartisan Publishers
| Title | Rouletabille at SemEval-2019 Task 4: Neural Network Baseline for Identification of Hyperpartisan Publishers |
| Authors | Jose G. Moreno, Yoann Pitarch, Karen Pinel-Sauvagnat, Gilles Hubert |
| Abstract | This paper describes the Rouletabille participation to the Hyperpartisan News Detection task. We propose the use of different text classification methods for this task. Preliminary experiments using a similar collection used in (Potthast et al., 2018) show that neural-based classification methods reach state-of-the art results. Our final submission is composed of a unique run that ranks among all runs at 3/49 position for the by-publisher test dataset and 43/96 for the by-article test dataset in terms of Accuracy. |
| Tasks | Text Classification |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2169/ |
| https://www.aclweb.org/anthology/S19-2169 | |
| PWC | https://paperswithcode.com/paper/rouletabille-at-semeval-2019-task-4-neural |
| Repo | |
| Framework | |
