Paper Group NANR 37
Reflective and Fluorescent Separation Under Narrow-Band Illumination. The Fallacy of Echo Chambers: Analyzing the Political Slants of User-Generated News Comments in Korean Media. Max-value Entropy Search for Multi-Objective Bayesian Optimization. Additive Compositionality of Word Vectors. Aligning Latent Spaces for 3D Hand Pose Estimation. SO-Hand …
Reflective and Fluorescent Separation Under Narrow-Band Illumination
| Title | Reflective and Fluorescent Separation Under Narrow-Band Illumination |
| Authors | Koji Koyamatsu, Daichi Hidaka, Takahiro Okabe, Hendrik P. A. Lensch |
| Abstract | In this paper, we address the separation of reflective and fluorescent components in RGB images taken under narrow-band light sources such as LEDs. First, we show that the fluorescent color per pixel can be estimated from at least two images under different light source colors, because the observed color at a surface point is represented by a convex combination of the light source color and the illumination-invariant fluorescent color. Second, we propose a method for robustly estimating the fluorescent color via MAP estimation by taking the prior knowledge with respect to fluorescent colors into consideration. We conducted a number of experiments by using both synthetic and real images, and confirmed that our proposed method works better than the closely related state-of-the-art method and enables us to separate reflective and fluorescent components even from a single image. Furthermore, we demonstrate that our method is effective for applications such as image-based material editing and relighting. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Koyamatsu_Reflective_and_Fluorescent_Separation_Under_Narrow-Band_Illumination_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Koyamatsu_Reflective_and_Fluorescent_Separation_Under_Narrow-Band_Illumination_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/reflective-and-fluorescent-separation-under |
| Repo | |
| Framework | |
The Fallacy of Echo Chambers: Analyzing the Political Slants of User-Generated News Comments in Korean Media
| Title | The Fallacy of Echo Chambers: Analyzing the Political Slants of User-Generated News Comments in Korean Media |
| Authors | Jiyoung Han, Youngin Lee, Junbum Lee, Meeyoung Cha |
| Abstract | This study analyzes the political slants of user comments on Korean partisan media. We built a BERT-based classifier to detect political leaning of short comments via the use of semi-unsupervised deep learning methods that produced an F1 score of 0.83. As a result of classifying 21.6K comments, we found the high presence of conservative bias on both conservative and liberal news outlets. Moreover, this study discloses an asymmetry across the partisan spectrum in that more liberals (48.0{%}) than conservatives (23.6{%}) comment not only on news stories resonating with their political perspectives but also on those challenging their viewpoints. These findings advance the current understanding of online echo chambers. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5548/ |
| https://www.aclweb.org/anthology/D19-5548 | |
| PWC | https://paperswithcode.com/paper/the-fallacy-of-echo-chambers-analyzing-the |
| Repo | |
| Framework | |
Max-value Entropy Search for Multi-Objective Bayesian Optimization
| Title | Max-value Entropy Search for Multi-Objective Bayesian Optimization |
| Authors | Syrine Belakaria, Aryan Deshwal, Janardhan Rao Doppa |
| Abstract | We consider the problem of multi-objective (MO) blackbox optimization using expensive function evaluations, where the goal is to approximate the true Pareto-set of solutions by minimizing the number of function evaluations. For example, in hardware design optimization, we need to find the designs that trade-off performance, energy, and area overhead using expensive simulations. We propose a novel approach referred to as Max-value Entropy Search for Multi-objective Optimization (MESMO) to solve this problem. MESMO employs an output-space entropy based acquisition function to efficiently select the sequence of inputs for evaluation for quickly uncovering high-quality solutions. We also provide theoretical analysis to characterize the efficacy of MESMO. Our experiments on several synthetic and real-world benchmark problems show that MESMO consistently outperforms state-of-the-art algorithms. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8997-max-value-entropy-search-for-multi-objective-bayesian-optimization |
| http://papers.nips.cc/paper/8997-max-value-entropy-search-for-multi-objective-bayesian-optimization.pdf | |
| PWC | https://paperswithcode.com/paper/max-value-entropy-search-for-multi-objective |
| Repo | |
| Framework | |
Additive Compositionality of Word Vectors
| Title | Additive Compositionality of Word Vectors |
| Authors | Yeon Seonwoo, Sungjoon Park, Dongkwan Kim, Alice Oh |
| Abstract | Additive compositionality of word embedding models has been studied from empirical and theoretical perspectives. Existing research on justifying additive compositionality of existing word embedding models requires a rather strong assumption of uniform word distribution. In this paper, we relax that assumption and propose more realistic conditions for proving additive compositionality, and we develop a novel word and sub-word embedding model that satisfies additive compositionality under those conditions. We then empirically show our model{'}s improved semantic representation performance on word similarity and noisy sentence similarity. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5551/ |
| https://www.aclweb.org/anthology/D19-5551 | |
| PWC | https://paperswithcode.com/paper/additive-compositionality-of-word-vectors |
| Repo | |
| Framework | |
Aligning Latent Spaces for 3D Hand Pose Estimation
| Title | Aligning Latent Spaces for 3D Hand Pose Estimation |
| Authors | Linlin Yang, Shile Li, Dongheui Lee, Angela Yao |
| Abstract | Hand pose estimation from monocular RGB inputs is a highly challenging task. Many previous works for monocular settings only used RGB information for training despite the availability of corresponding data in other modalities such as depth maps. In this work, we propose to learn a joint latent representation that leverages other modalities as weak labels to boost the RGB-based hand pose estimator. By design, our architecture is highly flexible in embedding various diverse modalities such as heat maps, depth maps and point clouds. In particular, we find that encoding and decoding the point cloud of the hand surface can improve the quality of the joint latent representation. Experiments show that with the aid of other modalities during training, our proposed method boosts the accuracy of RGB-based hand pose estimation systems and significantly outperforms state-of-the-art on two public benchmarks. |
| Tasks | Hand Pose Estimation, Pose Estimation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Yang_Aligning_Latent_Spaces_for_3D_Hand_Pose_Estimation_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Yang_Aligning_Latent_Spaces_for_3D_Hand_Pose_Estimation_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/aligning-latent-spaces-for-3d-hand-pose |
| Repo | |
| Framework | |
SO-HandNet: Self-Organizing Network for 3D Hand Pose Estimation With Semi-Supervised Learning
| Title | SO-HandNet: Self-Organizing Network for 3D Hand Pose Estimation With Semi-Supervised Learning |
| Authors | Yujin Chen, Zhigang Tu, Liuhao Ge, Dejun Zhang, Ruizhi Chen, Junsong Yuan |
| Abstract | 3D hand pose estimation has made significant progress recently, where Convolutional Neural Networks (CNNs) play a critical role. However, most of the existing CNN-based hand pose estimation methods depend much on the training set, while labeling 3D hand pose on training data is laborious and time-consuming. Inspired by the point cloud autoencoder presented in self-organizing network (SO-Net), our proposed SO-HandNet aims at making use of the unannotated data to obtain accurate 3D hand pose estimation in a semi-supervised manner. We exploit hand feature encoder (HFE) to extract multi-level features from hand point cloud and then fuse them to regress 3D hand pose by a hand pose estimator (HPE). We design a hand feature decoder (HFD) to recover the input point cloud from the encoded feature. Since the HFE and the HFD can be trained without 3D hand pose annotation, the proposed method is able to make the best of unannotated data during the training phase. Experiments on four challenging benchmark datasets validate that our proposed SO-HandNet can achieve superior performance for 3D hand pose estimation via semi-supervised learning. |
| Tasks | Hand Pose Estimation, Pose Estimation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Chen_SO-HandNet_Self-Organizing_Network_for_3D_Hand_Pose_Estimation_With_Semi-Supervised_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Chen_SO-HandNet_Self-Organizing_Network_for_3D_Hand_Pose_Estimation_With_Semi-Supervised_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/so-handnet-self-organizing-network-for-3d |
| Repo | |
| Framework | |
Learning to Minify Photometric Stereo
| Title | Learning to Minify Photometric Stereo |
| Authors | Junxuan Li, Antonio Robles-Kelly, Shaodi You, Yasuyuki Matsushita |
| Abstract | Photometric stereo estimates the surface normal given a set of images acquired under different illumination conditions. To deal with diverse factors involved in the image formation process, recent photometric stereo methods demand a large number of images as input. We propose a method that can dramatically decrease the demands on the number of images by learning the most informative ones under different illumination conditions. To this end, we use a deep learning framework to automatically learn the critical illumination conditions required at input. Furthermore, we present an occlusion layer that can synthesize cast shadows, which effectively improves the estimation accuracy. We assess our method on challenging real-world conditions, where we outperform techniques elsewhere in the literature with a significantly reduced number of light conditions. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Li_Learning_to_Minify_Photometric_Stereo_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Li_Learning_to_Minify_Photometric_Stereo_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-minify-photometric-stereo |
| Repo | |
| Framework | |
Provably Global Convergence of Actor-Critic: A Case for Linear Quadratic Regulator with Ergodic Cost
| Title | Provably Global Convergence of Actor-Critic: A Case for Linear Quadratic Regulator with Ergodic Cost |
| Authors | Zhuoran Yang, Yongxin Chen, Mingyi Hong, Zhaoran Wang |
| Abstract | Despite the empirical success of the actor-critic algorithm, its theoretical understanding lags behind. In a broader context, actor-critic can be viewed as an online alternating update algorithm for bilevel optimization, whose convergence is known to be fragile. To understand the instability of actor-critic, we focus on its application to linear quadratic regulators, a simple yet fundamental setting of reinforcement learning. We establish a nonasymptotic convergence analysis of actor- critic in this setting. In particular, we prove that actor-critic finds a globally optimal pair of actor (policy) and critic (action-value function) at a linear rate of convergence. Our analysis may serve as a preliminary step towards a complete theoretical understanding of bilevel optimization with nonconvex subproblems, which is NP-hard in the worst case and is often solved using heuristics. |
| Tasks | bilevel optimization |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9044-provably-global-convergence-of-actor-critic-a-case-for-linear-quadratic-regulator-with-ergodic-cost |
| http://papers.nips.cc/paper/9044-provably-global-convergence-of-actor-critic-a-case-for-linear-quadratic-regulator-with-ergodic-cost.pdf | |
| PWC | https://paperswithcode.com/paper/provably-global-convergence-of-actor-critic-a |
| Repo | |
| Framework | |
Neural Dependency Parsing of Biomedical Text: TurkuNLP entry in the CRAFT Structural Annotation Task
| Title | Neural Dependency Parsing of Biomedical Text: TurkuNLP entry in the CRAFT Structural Annotation Task |
| Authors | Thang Minh Ngo, Jenna Kanerva, Filip Ginter, Sampo Pyysalo |
| Abstract | We present the approach taken by the TurkuNLP group in the CRAFT Structural Annotation task, a shared task on dependency parsing. Our approach builds primarily on the Turku neural parser, a native dependency parser that ranked among the best in the recent CoNLL tasks on parsing Universal Dependencies. To adapt the parser to the biomedical domain, we considered and evaluated a number of approaches, including the generation of custom word embeddings, combination with other in-domain resources, and the incorporation of information from named entity recognition. We achieved a labeled attachment score of 89.7{%}, the best result among task participants. |
| Tasks | Dependency Parsing, Named Entity Recognition, Word Embeddings |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5728/ |
| https://www.aclweb.org/anthology/D19-5728 | |
| PWC | https://paperswithcode.com/paper/neural-dependency-parsing-of-biomedical-text |
| Repo | |
| Framework | |
Duluth at SemEval-2019 Task 6: Lexical Approaches to Identify and Categorize Offensive Tweets
| Title | Duluth at SemEval-2019 Task 6: Lexical Approaches to Identify and Categorize Offensive Tweets |
| Authors | Ted Pedersen |
| Abstract | This paper describes the Duluth systems that participated in SemEval{–}2019 Task 6, Identifying and Categorizing Offensive Language in Social Media (OffensEval). For the most part these systems took traditional Machine Learning approaches that built classifiers from lexical features found in manually labeled training data. However, our most successful system for classifying a tweet as offensive (or not) was a rule-based black{–}list approach, and we also experimented with combining the training data from two different but related SemEval tasks. Our best systems in each of the three OffensEval tasks placed in the middle of the comparative evaluation, ranking 57th of 103 in task A, 39th of 75 in task B, and 44th of 65 in task C. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2106/ |
| https://www.aclweb.org/anthology/S19-2106 | |
| PWC | https://paperswithcode.com/paper/duluth-at-semeval-2019-task-6-lexical |
| Repo | |
| Framework | |
Transfer Learning for Health-related Twitter Data
| Title | Transfer Learning for Health-related Twitter Data |
| Authors | Anne Dirkson, Suzan Verberne |
| Abstract | Transfer learning is promising for many NLP applications, especially in tasks with limited labeled data. This paper describes the methods developed by team TMRLeiden for the 2019 Social Media Mining for Health Applications (SMM4H) Shared Task. Our methods use state-of-the-art transfer learning methods to classify, extract and normalise adverse drug effects (ADRs) and to classify personal health mentions from health-related tweets. The code and fine-tuned models are publicly available. |
| Tasks | Transfer Learning |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3212/ |
| https://www.aclweb.org/anthology/W19-3212 | |
| PWC | https://paperswithcode.com/paper/transfer-learning-for-health-related-twitter |
| Repo | |
| Framework | |
NLP@UNED at SMM4H 2019: Neural Networks Applied to Automatic Classifications of Adverse Effects Mentions in Tweets
| Title | NLP@UNED at SMM4H 2019: Neural Networks Applied to Automatic Classifications of Adverse Effects Mentions in Tweets |
| Authors | Javier Cortes-Tejada, Juan Martinez-Romo, Lourdes Araujo |
| Abstract | This paper describes a system for automatically classifying adverse effects mentions in tweets developed for the task 1 at Social Media Mining for Health Applications (SMM4H) Shared Task 2019. We have developed a system based on LSTM neural networks inspired by the excellent results obtained by deep learning classifiers in the last edition of this task. The network is trained along with Twitter GloVe pre-trained word embeddings. |
| Tasks | Word Embeddings |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3213/ |
| https://www.aclweb.org/anthology/W19-3213 | |
| PWC | https://paperswithcode.com/paper/nlpuned-at-smm4h-2019-neural-networks-applied |
| Repo | |
| Framework | |
LaSTUS/TALN at SemEval-2019 Task 6: Identification and Categorization of Offensive Language in Social Media with Attention-based Bi-LSTM model
| Title | LaSTUS/TALN at SemEval-2019 Task 6: Identification and Categorization of Offensive Language in Social Media with Attention-based Bi-LSTM model |
| Authors | Lutfiye Seda Mut Altin, {`A}lex Bravo Serrano, Horacio Saggion |
| Abstract | We present a bidirectional Long-Short Term Memory network for identifying offensive language in Twitter. Our system has been developed in the context of the SemEval 2019 Task 6 which comprises three different sub-tasks, namely A: Offensive Language Detection, B: Categorization of Offensive Language, C: Offensive Language Target Identification. We used a pre-trained Word Embeddings in tweet data, including information about emojis and hashtags. Our approach achieves good performance in the three sub-tasks. |
| Tasks | Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2120/ |
| https://www.aclweb.org/anthology/S19-2120 | |
| PWC | https://paperswithcode.com/paper/lastustaln-at-semeval-2019-task-6 |
| Repo | |
| Framework | |
Prior-Free Dynamic Auctions with Low Regret Buyers
| Title | Prior-Free Dynamic Auctions with Low Regret Buyers |
| Authors | Yuan Deng, Jon Schneider, Balasubramanian Sivan |
| Abstract | We study the problem of how to repeatedly sell to a buyer running a no-regret, mean-based algorithm. Previous work [Braverman et al., 2018] shows that it is possible to design effective mechanisms in such a setting that extract almost all of the economic surplus, but these mechanisms require the buyer’s values each round to be drawn independently and identically from a fixed distribution. In this work, we do away with this assumption and consider the prior-free setting where the buyer’s value each round is chosen adversarially (possibly adaptively). We show that even in this prior-free setting, it is possible to extract a $(1-\varepsilon)$-approximation of the full economic surplus for any $\varepsilon > 0$. The number of options offered to a buyer in any round scales independently of the number of rounds $T$ and polynomially in $\varepsilon$. We show that this is optimal up to a polynomial factor; any mechanism achieving this approximation factor, even when values are drawn stochastically, requires at least $\Omega(1/\varepsilon)$ options. Finally, we examine what is possible when we constrain our mechanism to a natural auction format where overbidding is dominated. Braverman et al. [2018] show that even when values are drawn from a known stochastic distribution supported on $[1/H, 1]$, it is impossible in general to extract more than $O(\log\log H / \log H)$ of the economic surplus. We show how to achieve the same approximation factor in the prior-independent setting (where the distribution is unknown to the seller), and an approximation factor of $O(1 / \log H)$ in the prior-free setting (where the values are chosen adversarially). |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8727-prior-free-dynamic-auctions-with-low-regret-buyers |
| http://papers.nips.cc/paper/8727-prior-free-dynamic-auctions-with-low-regret-buyers.pdf | |
| PWC | https://paperswithcode.com/paper/prior-free-dynamic-auctions-with-low-regret |
| Repo | |
| Framework | |
Artificial Error Generation with Fluency Filtering
| Title | Artificial Error Generation with Fluency Filtering |
| Authors | Mengyang Qiu, Jungyeul Park |
| Abstract | The quantity and quality of training data plays a crucial role in grammatical error correction (GEC). However, due to the fact that obtaining human-annotated GEC data is both time-consuming and expensive, several studies have focused on generating artificial error sentences to boost training data for grammatical error correction, and shown significantly better performance. The present study explores how fluency filtering can affect the quality of artificial errors. By comparing artificial data filtered by different levels of fluency, we find that artificial error sentences with low fluency can greatly facilitate error correction, while high fluency errors introduce more noise. |
| Tasks | Grammatical Error Correction |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4408/ |
| https://www.aclweb.org/anthology/W19-4408 | |
| PWC | https://paperswithcode.com/paper/artificial-error-generation-with-fluency |
| Repo | |
| Framework | |
