Paper Group NANR 198
Gesture Recognition: Focus on the Hands. PDF-to-Text Reanalysis for Linguistic Data Mining. Examining Temporality in Document Classification. Fine-grained Semantic Textual Similarity for Serbian. SINT++: Robust Visual Tracking via Adversarial Positive Instance Generation. LatentPoison – Adversarial Attacks On The Latent Space. Learning Hidden Unit …
Gesture Recognition: Focus on the Hands
| Title | Gesture Recognition: Focus on the Hands |
| Authors | Pradyumna Narayana, Ross Beveridge, Bruce A. Draper |
| Abstract | Gestures are a common form of human communication and important for human computer interfaces (HCI). Recent approaches to gesture recognition use deep learning methods, including multi-channel methods. We show that when spatial channels are focused on the hands, gesture recognition improves significantly, particularly when the channels are fused using a sparse network. Using this technique, we improve performance on the ChaLearn IsoGD dataset from a previous best of 67.71% to 82.07%, and on the NVIDIA dataset from 83.8% to 91.28%. |
| Tasks | Gesture Recognition |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Narayana_Gesture_Recognition_Focus_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Narayana_Gesture_Recognition_Focus_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/gesture-recognition-focus-on-the-hands |
| Repo | |
| Framework | |
PDF-to-Text Reanalysis for Linguistic Data Mining
| Title | PDF-to-Text Reanalysis for Linguistic Data Mining |
| Authors | Michael Wayne Goodman, Ryan Georgi, Fei Xia |
| Abstract | |
| Tasks | Optical Character Recognition |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1116/ |
| https://www.aclweb.org/anthology/L18-1116 | |
| PWC | https://paperswithcode.com/paper/pdf-to-text-reanalysis-for-linguistic-data |
| Repo | |
| Framework | |
Examining Temporality in Document Classification
| Title | Examining Temporality in Document Classification |
| Authors | Xiaolei Huang, Michael J. Paul |
| Abstract | Many corpora span broad periods of time. Language processing models trained during one time period may not work well in future time periods, and the best model may depend on specific times of year (e.g., people might describe hotels differently in reviews during the winter versus the summer). This study investigates how document classifiers trained on documents from certain time intervals perform on documents from other time intervals, considering both seasonal intervals (intervals that repeat across years, e.g., winter) and non-seasonal intervals (e.g., specific years). We show experimentally that classification performance varies over time, and that performance can be improved by using a standard domain adaptation approach to adjust for changes in time. |
| Tasks | Document Classification, Domain Adaptation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-2110/ |
| https://www.aclweb.org/anthology/P18-2110 | |
| PWC | https://paperswithcode.com/paper/examining-temporality-in-document |
| Repo | |
| Framework | |
Fine-grained Semantic Textual Similarity for Serbian
| Title | Fine-grained Semantic Textual Similarity for Serbian |
| Authors | Vuk Batanovi{'c}, Milo{\v{s}} Cvetanovi{'c}, Bo{\v{s}}ko Nikoli{'c} |
| Abstract | |
| Tasks | Information Retrieval, Machine Translation, Natural Language Inference, Question Answering, Semantic Textual Similarity |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1219/ |
| https://www.aclweb.org/anthology/L18-1219 | |
| PWC | https://paperswithcode.com/paper/fine-grained-semantic-textual-similarity-for |
| Repo | |
| Framework | |
SINT++: Robust Visual Tracking via Adversarial Positive Instance Generation
| Title | SINT++: Robust Visual Tracking via Adversarial Positive Instance Generation |
| Authors | Xiao Wang, Chenglong Li, Bin Luo, Jin Tang |
| Abstract | Existing visual trackers are easily disturbed by occlusion,blurandlargedeformation. Inthechallengesofocclusion, motion blur and large object deformation, the performance of existing visual trackers may be limited due to the followingissues: i)Adoptingthedensesamplingstrategyto generate positive examples will make them less diverse; ii) Thetrainingdatawithdifferentchallengingfactorsarelimited, even though through collecting large training dataset. Collecting even larger training dataset is the most intuitive paradigm, but it may still can not cover all situations and the positive samples are still monotonous. In this paper, we propose to generate hard positive samples via adversarial learning for visual tracking. Speciï¬cally speaking, we assume the target objects all lie on a manifold, hence, we introduce the positive samples generation network (PSGN) to sampling massive diverse training data through traversing over the constructed target object manifold. The generated diverse target object images can enrich the training dataset and enhance the robustness of visual trackers. To make the tracker more robust to occlusion, we adopt the hard positive transformation network (HPTN) which can generate hard samples for tracking algorithm to recognize. We train this network with deep reinforcement learning to automaticallyoccludethetargetobjectwithanegativepatch. Based on the generated hard positive samples, we train a Siamese network for visual tracking and our experiments validate the effectiveness of the introduced algorithm. |
| Tasks | Visual Tracking |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Wang_SINT_Robust_Visual_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_SINT_Robust_Visual_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/sint-robust-visual-tracking-via-adversarial |
| Repo | |
| Framework | |
LatentPoison – Adversarial Attacks On The Latent Space
| Title | LatentPoison – Adversarial Attacks On The Latent Space |
| Authors | Antonia Creswell, Biswa Sengupta, Anil A. Bharath |
| Abstract | Robustness and security of machine learning (ML) systems are intertwined, wherein a non-robust ML system (classifiers, regressors, etc.) can be subject to attacks using a wide variety of exploits. With the advent of scalable deep learning methodologies, a lot of emphasis has been put on the robustness of supervised, unsupervised and reinforcement learning algorithms. Here, we study the robustness of the latent space of a deep variational autoencoder (dVAE), an unsupervised generative framework, to show that it is indeed possible to perturb the latent space, flip the class predictions and keep the classification probability approximately equal before and after an attack. This means that an agent that looks at the outputs of a decoder would remain oblivious to an attack. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=B1tExikAW |
| https://openreview.net/pdf?id=B1tExikAW | |
| PWC | https://paperswithcode.com/paper/latentpoison-adversarial-attacks-on-the-1 |
| Repo | |
| Framework | |
Learning Hidden Unit Contribution for Adapting Neural Machine Translation Models
| Title | Learning Hidden Unit Contribution for Adapting Neural Machine Translation Models |
| Authors | David Vilar |
| Abstract | In this paper we explore the use of Learning Hidden Unit Contribution for the task of neural machine translation. The method was initially proposed in the context of speech recognition for adapting a general system to the specific acoustic characteristics of each speaker. Similar in spirit, in a machine translation framework we want to adapt a general system to a specific domain. We show that the proposed method achieves improvements of up to 2.6 BLEU points over a general system, and up to 6 BLEU points if the initial system has only been trained on out-of-domain data, a situation which may easily happen in practice. The good performance together with its short training time and small memory footprint make it a very attractive solution for domain adaptation. |
| Tasks | Domain Adaptation, Machine Translation, Speech Recognition |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-2080/ |
| https://www.aclweb.org/anthology/N18-2080 | |
| PWC | https://paperswithcode.com/paper/learning-hidden-unit-contribution-for |
| Repo | |
| Framework | |
Provable Fast Greedy Compressive Summarization with Any Monotone Submodular Function
| Title | Provable Fast Greedy Compressive Summarization with Any Monotone Submodular Function |
| Authors | Shinsaku Sakaue, Tsutomu Hirao, Masaaki Nishino, Masaaki Nagata |
| Abstract | Submodular maximization with the greedy algorithm has been studied as an effective approach to extractive summarization. This approach is known to have three advantages: its applicability to many useful submodular objective functions, the efficiency of the greedy algorithm, and the provable performance guarantee. However, when it comes to compressive summarization, we are currently missing a counterpart of the extractive method based on submodularity. In this paper, we propose a fast greedy method for compressive summarization. Our method is applicable to any monotone submodular objective function, including many functions well-suited for document summarization. We provide an approximation guarantee of our greedy algorithm. Experiments show that our method is about 100 to 400 times faster than an existing method based on integer-linear-programming (ILP) formulations and that our method empirically achieves more than 95{%}-approximation. |
| Tasks | Document Summarization, Information Retrieval |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1157/ |
| https://www.aclweb.org/anthology/N18-1157 | |
| PWC | https://paperswithcode.com/paper/provable-fast-greedy-compressive |
| Repo | |
| Framework | |
Revisiting Knowledge Base Embedding as Tensor Decomposition
| Title | Revisiting Knowledge Base Embedding as Tensor Decomposition |
| Authors | Jiezhong Qiu, Hao Ma, Yuxiao Dong, Kuansan Wang, Jie Tang |
| Abstract | We study the problem of knowledge base (KB) embedding, which is usually addressed through two frameworks—neural KB embedding and tensor decomposition. In this work, we theoretically analyze the neural embedding framework and subsequently connect it with tensor based embedding. Specifically, we show that in neural KB embedding the two commonly adopted optimization solutions—margin-based and negative sampling losses—are closely related to each other. We also reach the closed-form tensor that is implicitly approximated by popular neural KB approaches, revealing the underlying connection between neural and tensor based KB embedding models. Grounded in the theoretical results, we further present a tensor decomposition based framework KBTD to directly approximate the derived closed form tensor. Under this framework, the neural KB embedding models, such as NTN, TransE, Bilinear, and DISTMULT, are unified into a general tensor optimization architecture. Finally, we conduct experiments on the link prediction task in WordNet and Freebase, empirically demonstrating the effectiveness of the KBTD framework. |
| Tasks | Link Prediction |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=S1sRrN-CW |
| https://openreview.net/pdf?id=S1sRrN-CW | |
| PWC | https://paperswithcode.com/paper/revisiting-knowledge-base-embedding-as-tensor |
| Repo | |
| Framework | |
Automated Fact-Checking of Claims in Argumentative Parliamentary Debates
| Title | Automated Fact-Checking of Claims in Argumentative Parliamentary Debates |
| Authors | Nona Naderi, Graeme Hirst |
| Abstract | We present an automated approach to distinguish true, false, stretch, and dodge statements in questions and answers in the Canadian Parliament. We leverage the truthfulness annotations of a U.S. fact-checking corpus by training a neural net model and incorporating the prediction probabilities into our models. We find that in concert with other linguistic features, these probabilities can improve the multi-class classification results. We further show that dodge statements can be detected with an F1 measure as high as 82.57{%} in binary classification settings. |
| Tasks | Semantic Textual Similarity |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-5509/ |
| https://www.aclweb.org/anthology/W18-5509 | |
| PWC | https://paperswithcode.com/paper/automated-fact-checking-of-claims-in |
| Repo | |
| Framework | |
CoNLL-UL: Universal Morphological Lattices for Universal Dependency Parsing
| Title | CoNLL-UL: Universal Morphological Lattices for Universal Dependency Parsing |
| Authors | Amir More, {"O}zlem {\c{C}}etino{\u{g}}lu, {\c{C}}a{\u{g}}r{\i} {\c{C}}{"o}ltekin, Nizar Habash, Beno{^\i}t Sagot, Djam{'e} Seddah, Dima Taji, Reut Tsarfaty |
| Abstract | |
| Tasks | Dependency Parsing, Morphological Analysis, Part-Of-Speech Tagging |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1608/ |
| https://www.aclweb.org/anthology/L18-1608 | |
| PWC | https://paperswithcode.com/paper/conll-ul-universal-morphological-lattices-for |
| Repo | |
| Framework | |
K-convexity shape priors for segmentation
| Title | K-convexity shape priors for segmentation |
| Authors | Hossam Isack, Lena Gorelick, Karin Ng, Olga Veksler, Yuri Boykov |
| Abstract | This work extends popular star-convexity and other more general forms of convexity priors. We represent an object as a union of “convex’’ overlappable subsets. Since an arbitrary shape can always be divided into convex parts, our regularization model restricts the number of such parts. Previous k-part shape priors are limited to disjoint parts. For example, one approach segments an object via optimizing its $k$-coverage by disjoint convex parts, which we show is highly sensitive to local minima. In contrast, our shape model allows the convex parts to overlap, which both relaxes and simplifies the coverage problem, e.g. fewer parts are needed to represent any object. As shown in the paper, for many forms of convexity our regularization model is significantly more descriptive for any given k. Our shape prior is useful in practice, e.g. in biomedical applications, and its optimization is robust to local minima. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Hossam_Isack_K-convexity_shape_priors_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Hossam_Isack_K-convexity_shape_priors_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/k-convexity-shape-priors-for-segmentation |
| Repo | |
| Framework | |
Mutux at SemEval-2018 Task 1: Exploring Impacts of Context Information On Emotion Detection
| Title | Mutux at SemEval-2018 Task 1: Exploring Impacts of Context Information On Emotion Detection |
| Authors | Pan Du, Jian-Yun Nie |
| Abstract | This paper describes MuTuX, our system that is designed for task 1-5a, emotion classification analysis of tweets on SemEval2018. The system aims at exploring the potential of context information of terms for emotion analysis. A Recurrent Neural Network is adopted to capture the context information of terms in tweets. Only term features and the sequential relations are used in our system. The results submitted ranks 16th out of 35 systems on the task of emotion detection in English-language tweets. |
| Tasks | Emotion Classification, Emotion Recognition, Product Recommendation, Sentiment Analysis |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1052/ |
| https://www.aclweb.org/anthology/S18-1052 | |
| PWC | https://paperswithcode.com/paper/mutux-at-semeval-2018-task-1-exploring |
| Repo | |
| Framework | |
Structured Exploration via Hierarchical Variational Policy Networks
| Title | Structured Exploration via Hierarchical Variational Policy Networks |
| Authors | Stephan Zheng, Yisong Yue |
| Abstract | Reinforcement learning in environments with large state-action spaces is challenging, as exploration can be highly inefficient. Even if the dynamics are simple, the optimal policy can be combinatorially hard to discover. In this work, we propose a hierarchical approach to structured exploration to improve the sample efficiency of on-policy exploration in large state-action spaces. The key idea is to model a stochastic policy as a hierarchical latent variable model, which can learn low-dimensional structure in the state-action space, and to define exploration by sampling from the low-dimensional latent space. This approach enables lower sample complexity, while preserving policy expressivity. In order to make learning tractable, we derive a joint learning and exploration strategy by combining hierarchical variational inference with actor-critic learning. The benefits of our learning approach are that 1) it is principled, 2) simple to implement, 3) easily scalable to settings with many actions and 4) easily composable with existing deep learning approaches. We demonstrate the effectiveness of our approach on learning a deep centralized multi-agent policy, as multi-agent environments naturally have an exponentially large state-action space. In this setting, the latent hierarchy implements a form of multi-agent coordination during exploration and execution (MACE). We demonstrate empirically that MACE can more efficiently learn optimal policies in challenging multi-agent games with a large number (~20) of agents, compared to conventional baselines. Moreover, we show that our hierarchical structure leads to meaningful agent coordination. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=HyunpgbR- |
| https://openreview.net/pdf?id=HyunpgbR- | |
| PWC | https://paperswithcode.com/paper/structured-exploration-via-hierarchical |
| Repo | |
| Framework | |
Improved large-scale graph learning through ridge spectral sparsification
| Title | Improved large-scale graph learning through ridge spectral sparsification |
| Authors | Daniele Calandriello, Alessandro Lazaric, Ioannis Koutis, Michal Valko |
| Abstract | The representation and learning benefits of methods based on graph Laplacians, such as Laplacian smoothing or harmonic function solution for semi-supervised learning (SSL), are empirically and theoretically well supported. Nonetheless, the exact versions of these methods scale poorly with the number of nodes $n$ of the graph. In this paper, we combine a spectral sparsification routine with Laplacian learning. Given a graph $G$ as input, our algorithm computes a sparsifier in a distributed way in $O(n\log^3(n))$ time, $O(m\log^3(n))$ work and $O(n\log(n))$ memory, using only $\log(n)$ rounds of communication. Furthermore, motivated by the regularization often employed in learning algorithms, we show that constructing sparsifiers that preserve the spectrum of the Laplacian only up to the regularization level may drastically reduce the size of the final graph. By constructing a spectrally-similar graph, we are able to bound the error induced by the sparsification for a variety of downstream tasks (e.g., SSL). We empirically validate the theoretical guarantees on Amazon co-purchase graph and compare to the state-of-the-art heuristics. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2371 |
| http://proceedings.mlr.press/v80/calandriello18a/calandriello18a.pdf | |
| PWC | https://paperswithcode.com/paper/improved-large-scale-graph-learning-through |
| Repo | |
| Framework | |
